{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Version 1 Simulation\n",
    "\n",
    "The first version of this series is a basic control model. Given an elevation profile $H(x)$ and a time target, minimize energy usage.\n",
    "We assume the time target is constant, since we are racing at a given overall pace. In other words, we already know the average speed $E(V) = dist/time$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import jax.numpy as jnp\n",
    "from jax import jit, vmap, lax\n",
    "from jax import random\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "@jit\n",
    "def _cov_math(t, s, H):\n",
    "    return 0.5 * (jnp.abs(t) ** 2 * H + jnp.abs(s) ** 2 * H - jnp.abs(t - s) ** 2 * H)\n",
    "\n",
    "\n",
    "def _fbm_covariance(n, H) -> jnp.ndarray:\n",
    "    tidx = jnp.arange(1, n + 1)\n",
    "    t, s = jnp.meshgrid(tidx, tidx)\n",
    "\n",
    "    # fBm covariance equation from wikipedia\n",
    "    cov = 0.5 * (jnp.abs(t) ** 2 * H + jnp.abs(s) ** 2 * H - jnp.abs(t - s) ** 2 * H)\n",
    "    return cov\n",
    "\n",
    "# generate terrain using fractional brownian motion\n",
    "def gen_elevation_profile(rngkey: random.PRNGKey, n_steps: int, H: float):\n",
    "    t = jnp.linspace(0,1,n_steps)\n",
    "    cov = _fbm_covariance(n_steps, H)\n",
    "    # using the \"method 1\" (cholesky decomposition)\n",
    "    sigma = jnp.linalg.cholesky(cov)\n",
    "    # create a vector of n_steps gaussian normal values\n",
    "    v = random.normal(rngkey, shape=(n_steps))\n",
    "    # convert these to fbm lines\n",
    "\n",
    "    fbm_samples = sigma * v\n",
    "\n",
    "    return t, fbm_samples\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "An NVIDIA GPU may be present on this machine, but a CUDA-enabled jaxlib is not installed. Falling back to cpu.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[nan -0. -0. ... -0. -0. -0.]\n",
      " [nan nan -0. ... -0. -0. -0.]\n",
      " [nan nan nan ... -0. -0. -0.]\n",
      " ...\n",
      " [nan nan nan ... nan -0. -0.]\n",
      " [nan nan nan ... nan nan -0.]\n",
      " [nan nan nan ... nan nan nan]]\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "key = random.PRNGKey(0)\n",
    "steps = 1000\n",
    "samples = 5\n",
    "\n",
    "H = 0.6\n",
    "\n",
    "t, fbm = gen_elevation_profile(key, steps, H)\n",
    "plt.figure(figsize=(12,6))\n",
    "print(fbm)\n",
    "for i in range(fbm.shape[0]):\n",
    "    plt.plot(t, fbm[i], label=f\"Sample {i}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x7101983fd730>]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "steps = 100\n",
    "key = random.key(25)\n",
    "\n",
    "def uniform_window(n):\n",
    "    return jnp.ones(n)/n\n",
    "\n",
    "def generate_basic_terrain(key, steps=100, yscale=1.0, xscale=10.0, window=uniform_window, window_size=5):\n",
    "    key, split = random.split(key)\n",
    "    v = random.normal(split, shape=(steps))\n",
    "    y = jnp.cumsum(v) * yscale\n",
    "    # smooth with a windowing function\n",
    "    y_smooth = jnp.convolve(y, window(window_size), mode='same')\n",
    "    # compute the x-values\n",
    "    x = jnp.arange(steps) * xscale\n",
    "    return x,y_smooth\n",
    "\n",
    "\n",
    "x,y = generate_basic_terrain(key)\n",
    "    \n",
    "slope = jnp.atan(jnp.diff(y, prepend=0) / 10.0) * 180 / jnp.pi\n",
    "plt.plot(x,y)\n",
    "plt.plot(x, slope)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x7101ac7f1070>]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# we can compute the slope at any point along the terrain\n",
    "plt.plot(x, slope)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "%run ../src/solarcarsim/physsim.py"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CarParams(mass=800, frontal_area=1.3, drag_coeff=0.18, rolling_coeff=0.002, moter_eff=0.93, wheel_radius=0.23, max_speed=30.0, solar_area=5.0, solar_eff=0.2, n_motors=2, motor=MotorParams(kv=8.43, kt=1.1, resistance=100.0, friction_coeff=0.001, iron_coeff=0.001), battery=BatteryParams(shape=(36, 19), resistance=0.0126, initial_energy=66600.0))\n"
     ]
    }
   ],
   "source": [
    "from functools import partial\n",
    "import jax\n",
    "p = CarParams()\n",
    "print(p)\n",
    "\n",
    "\n",
    "def control_fn(time):\n",
    "    # for the first minute, go at 15 m/s\n",
    "    return 10 + time * 10/60\n",
    "\n",
    "def wrapper(curr_state, _):\n",
    "    vel = control_fn(curr_state[1])\n",
    "    next_state = forward(curr_state, 0.1, vel, p)\n",
    "    return next_state, next_state\n",
    "\n",
    "state_init = jnp.array([0.0, 0.0, 45.5e6])\n",
    "_, out = jax.lax.scan(wrapper, state_init, None, length=1000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x7101ac1667b0>]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax1 = plt.subplots()\n",
    "ax2 = ax1.twinx()\n",
    "x = out[:,1]\n",
    "ax1.plot(x, out[:,0], label=\"position\")\n",
    "ax2.plot(x, out[:,2], label=\"energy\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "x = jnp.linspace(0,30, 1000)\n",
    "dragf = drag_force(x, 1.3, 0.18, 1.184)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x7101a4010b30>]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAigAAAGdCAYAAAA44ojeAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAAA9hAAAPYQGoP6dpAABA4ElEQVR4nO3dd3wUdeLG8c+mbUIqSUiDBALSS+gxdiUnqKcgcIKioiKcCipiAfwdKJ6Ih54iNs6KBbGdoOLJHaKAJQQIvYUWIJQEQshuCqk7vz+iexdFCLDJ7CbP+/XaV5LZyeTJMLAPs9/5jsUwDAMRERERN+JldgARERGRX1NBEREREbejgiIiIiJuRwVFRERE3I4KioiIiLgdFRQRERFxOyooIiIi4nZUUERERMTt+Jgd4Gw4HA4OHTpEcHAwFovF7DgiIiJSC4ZhUFhYSFxcHF5epz5H4pEF5dChQ8THx5sdQ0RERM5CdnY2LVq0OOU6HllQgoODgepfMCQkxOQ0IiIiUht2u534+Hjn6/ipeGRB+eVtnZCQEBUUERERD1Ob4RkaJCsiIiJuRwVFRERE3I4KioiIiLgdFRQRERFxOyooIiIi4nZUUERERMTtqKCIiIiI21FBEREREbejgiIiIiJuRwVFRERE3I4KioiIiLgdFRQRERFxOyooIiIi4nTYdoKbXl/JjtxCU3OooIiIiAgAhmEw8Z+b+Gn3MaYs3GxqFhUUERERAeCj1dms2HEUq48XTw3uamoWFRQREREhO7+Evy7aCsDD/dvTplmQqXlUUERERBo5h8Pg4U83UFxeRZ9WTbn9wkSzI6mgiIiINHbvpO1l5Z58mvh58+yfkvD2spgdSQVFRESkMdt9tIinv94OwKNXd6RlRKDJiaqpoIiIiDRSlVUOHvx4A2WVDi5uG8mI5ASzIzmpoIiIiDRS/1ixh/XZBQT7+zBzaDcsFvPf2vmFCoqIiEgjtPWQnVnf7ABg2nWdiQ0NMDlRTWdcUFasWMG1115LXFwcFouFhQsXOp+rqKhg4sSJdO3alcDAQOLi4rj11ls5dOhQjW3k5+czYsQIQkJCCAsLY9SoURQVFZ3zLyMiIiKnV17pYMLH66moMriyUzTX92hudqTfOOOCUlxcTFJSEi+//PJvnispKWHt2rVMmTKFtWvX8tlnn5GZmcl1111XY70RI0awZcsWlixZwqJFi1ixYgVjxow5+99CREREau2FpTvYnlNIeKAfTw3u6lZv7fzCYhiGcdbfbLGwYMECBg0a9LvrrF69mr59+7Jv3z4SEhLYtm0bnTp1YvXq1fTu3RuAxYsXc/XVV3PgwAHi4uJO+3PtdjuhoaHYbDZCQkLONr6IiEijs27/cYa8+hMOA+bc3JMBXWLr7Wefyet3nY9BsdlsWCwWwsLCAEhLSyMsLMxZTgBSU1Px8vIiPT39pNsoKyvDbrfXeIiIiMiZOVFexYMfb8BhwKDucfVaTs5UnRaU0tJSJk6cyI033uhsSjk5OURFRdVYz8fHh/DwcHJyck66nRkzZhAaGup8xMfH12VsERGRBmnmv7ezJ6+Y6BAr067rYnacU6qzglJRUcENN9yAYRi8+uqr57StyZMnY7PZnI/s7GwXpRQREWkcftqdx9s/7gXgb0O6EdrE19xAp+FTFxv9pZzs27ePb7/9tsb7TDExMRw5cqTG+pWVleTn5xMTE3PS7VmtVqxWa11EFRERafAKSyt4+JONANyUnMBl7aNO8x3mc/kZlF/Kyc6dO/nmm2+IiIio8XxKSgoFBQVkZGQ4l3377bc4HA6Sk5NdHUdERKTRm/7VNg4WnCA+PIBHr+5odpxaOeMzKEVFRezatcv5dVZWFuvXryc8PJzY2FiGDh3K2rVrWbRoEVVVVc5xJeHh4fj5+dGxY0cGDBjA6NGjmTNnDhUVFYwbN47hw4fX6goeERERqb3vth/hw9XZWCzw7NAkgqx18uaJy53xZcbLli3j8ssv/83ykSNH8vjjj5OYePJbNH/33XdcdtllQPVEbePGjePLL7/Ey8uLIUOGMHv2bIKCgmqVQZcZi4iInF5+cTn9Z63gaGEZoy5KZMofO5ma50xev89pHhSzqKCIiIicmmEY3PV+Bv/ekkvbqCC+vPci/H29Tc3kVvOgiIiISP37JOMA/96Si6+3hVnDu5teTs6UCoqIiEgDk51fwrQvtgAw4Q/t6RwXanKiM6eCIiIi0oBUOQwe+Gg9xeVV9G0VzphLWpsd6ayooIiIiDQgc5bvZs2+4wRZffj7DUl4e7nfjQBrQwVFRESkgdh80MbzS3YA8Ph1nYkPb2JyorOngiIiItIAlFZUMf6j9VQ6DK7qEsOQns3NjnROVFBEREQagKe/3s6uI0U0C7Yy/fquWCye+dbOL1RQREREPNz3O48y96e9ADwztBvhgX7mBnIBFRQREREPVlBSzkOfbADg1pSWHnEjwNpQQREREfFQhmHwfws3k2svo3WzQCZf5Rk3AqwNFRQREREPtXD9Qb7aeBgfLwuzhnUnwM+zZos9FRUUERERD3TgeAlTF1bPFnt/v7Z0axFmbiAXU0ERERHxMA6HwYMfb6CwrJKeCWHcfVkbsyO5nAqKiIiIh3n9+z2kZ+XTxM+b54d1x8e74b2cN7zfSEREpAHbdMDGs//JBGDqHzvRMiLQ5ER1QwVFRETEQ5SUV3L/h+uoqDIY0DmGYX3izY5UZ1RQREREPMQTX25lT14xMSH+PD3E82eLPRUVFBEREQ/w9abDfLg6G4sFnh/WnbAmnj9b7KmooIiIiLi5QwUnmPTZJgDuvrQNKW0iTE5U91RQRERE3FiVw2DCx+uxnaggqUUoD/yhndmR6oUKioiIiBubs3w3K/dUX1L8wvAe+DbAS4pPpnH8liIiIh5ofXYBzy/ZAcC06zrTKrJhXlJ8MiooIiIibqiorPqS4kqHwTXdYhnaq4XZkeqVCoqIiIgbevyLLew7VkJcqD9PDWrYlxSfjAqKiIiIm/lywyE+zTiAlwVmDe9BaBNfsyPVOxUUERERN3LgeAmPLqi+pHjs5efRNzHc5ETmUEERERFxE1UOgwc+Wk9haSU9EsK4r19bsyOZRgVFRETETbz83S5W7z1OkNWHF4Y1nkuKT6bx/uYiIiJuJGPfcV5YuhOAJwZ2JiGiicmJzKWCIiIiYjJbSQX3zV9HlcPguqQ4ru/R3OxIplNBERERMZFhGEz6bCMHC07QMqIJ06/v0uguKT4ZFRQRERETvZ++n6835+DrbeHFG3sQ7N/4Lik+GRUUERERk2w7bOevi7YCMHFAB7q1CDM3kBtRQRERETFBSXkl4z5YS3mlgys6RDHqokSzI7kVFRQRERETPP7FFnYfLSY6xMozQ7tp3MmvqKCIiIjUs8/XH+TjNQewWGDWsB5EBFnNjuR2VFBERETq0d68Yv5vwWYA7r2iLSltIkxO5J5UUEREROpJeaWDe+evo6iskr6twrnvivPMjuS2VFBERETqyczF29l00EZYE19euLE7Po14KvvT0Z4RERGpB99uz+WNH7IAeHZoErGhASYncm8qKCIiInUsx1bKgx9vAOD2C1uR2ina5ETuTwVFRESkDlU5DO7/cB3HSyroHBfCpKs6mB3JI6igiIiI1KGXvt1FelY+gX7evHRTT6w+3mZH8ghnXFBWrFjBtddeS1xcHBaLhYULF9Z43jAMpk6dSmxsLAEBAaSmprJz584a6+Tn5zNixAhCQkIICwtj1KhRFBUVndMvIiIi4m7Sdh/jhaU7AHjy+i4kRgaanMhznHFBKS4uJikpiZdffvmkz8+cOZPZs2czZ84c0tPTCQwMpH///pSWljrXGTFiBFu2bGHJkiUsWrSIFStWMGbMmLP/LURERNzM0cIy7vtwHQ4DhvRswfU9WpgdyaNYDMMwzvqbLRYWLFjAoEGDgOqzJ3FxcTz44IM89NBDANhsNqKjo5k7dy7Dhw9n27ZtdOrUidWrV9O7d28AFi9ezNVXX82BAweIi4s77c+12+2EhoZis9kICQk52/giIiJ1osphcOtb6fy46xjtooNYOPZCmvj5mB3LdGfy+u3SMShZWVnk5OSQmprqXBYaGkpycjJpaWkApKWlERYW5iwnAKmpqXh5eZGenn7S7ZaVlWG322s8RERE3NXspTv5cdcxmvh588qInionZ8GlBSUnJweA6Oial09FR0c7n8vJySEqKqrG8z4+PoSHhzvX+bUZM2YQGhrqfMTHx7sytoiIiMv8sDOP2d9Wj72cfn0XzosKNjmRZ/KIq3gmT56MzWZzPrKzs82OJCIi8htH7KWM/2gdhgHD+8Rr3Mk5cGlBiYmJASA3N7fG8tzcXOdzMTExHDlypMbzlZWV5OfnO9f5NavVSkhISI2HiIiIO6msqr7PTl5ROR1ignn8us5mR/JoLi0oiYmJxMTEsHTpUucyu91Oeno6KSkpAKSkpFBQUEBGRoZznW+//RaHw0FycrIr44iIiNSbWd/sdM538sqInvj7ar6Tc3HGo3aKiorYtWuX8+usrCzWr19PeHg4CQkJjB8/nieffJK2bduSmJjIlClTiIuLc17p07FjRwYMGMDo0aOZM2cOFRUVjBs3juHDh9fqCh4RERF3s3zHUV5eVv3a+PSQbrRuFmRyIs93xgVlzZo1XH755c6vJ0yYAMDIkSOZO3cujzzyCMXFxYwZM4aCggIuuugiFi9ejL+/v/N75s2bx7hx4+jXrx9eXl4MGTKE2bNnu+DXERERqV+HbSd44KP1GAbcfH4C1ybpP9uucE7zoJhF86CIiIg7qKhycONrK1mz7zid40L4590X6K2dUzBtHhQREZHG5Nn/ZLJm33GCrT4ad+JiKigiIiJnYem2XP6xfA8AM4d2o2WE7rPjSiooIiIiZ+hgwQke/GQDALdd0IqrusaanKjhUUERERE5A2WVVdwzby0FJRUktQjl0as7mh2pQVJBEREROQNPLtrGhuwCQgN8eemmnvj56KW0LmivioiI1NKCdQd4b+U+LBaYNbw78eFNzI7UYKmgiIiI1ML2HDuTP9sEwL1XtOXy9lGn+Q45FyooIiIip2EvreDu99dSWuHgknbNuL9fW7MjNXgqKCIiIqdgGAYPf7KBrLximocFMGtYd7y9LGbHavBUUERERE7htRV7+PeWXPy8vXhlRE/CA/3MjtQoqKCIiIj8jrTdx/jb4u0ATL22E0nxYeYGakRUUERERE4i117KvfPX4TBgcM/mjEhOMDtSo6KCIiIi8isVVQ7GzltLXlEZHWKCmT6oKxaLxp3UJxUUERGRX3n66+3OmwC+enMvAvx0E8D6poIiIiLyP77aeJg3f8gC4NkbkkiM1E0AzaCCIiIi8rNdR4p45NPqmwD++dLW9O8cY3KixksFRUREBCgqq+Su9zMoLq/i/NbhPHxle7MjNWoqKCIi0ugZhsFDH29g15EiokOsvHhjT3y89RJpJu19ERFp9F5ZtpvFW3Lw9bbw6s29aBZsNTtSo6eCIiIijdqyzCM8+59MAJ4Y2IWeCU1NTiSggiIiIo3YvmPF3Dd/HYYBN/ZN4Ma+mozNXaigiIhIo1RSXsmf38vAXlpJj4QwHr+uk9mR5H+ooIiISKNjGAaPfLqR7TmFRAZZeXVEL6w+mozNnaigiIhIo/PG91ks2ngYHy8Lr97ck5hQf7Mjya+ooIiISKPy4648Zny9Dai+Q3GfVuEmJ5KTUUEREZFG48DxEsZ9sBaHAUN7teCW81uaHUl+hwqKiIg0CqUVVfz5vQyOl1TQrUUoTw7qojsUuzEVFBERafAMw+DRzzax5ZCd8EA/Xr25F/6+GhTrzlRQRESkwXvnp718tu4g3l4WXrqpB83DAsyOJKehgiIiIg3ayj3HePKr6kGxj17dkQvaRJqcSGpDBUVERBqs7PwS7n4/g0qHwaDucdxxYSuzI0ktqaCIiEiDVFxWyeh31zgHxT49pJsGxXoQFRQREWlwHA6DCR+vd84U+49bNCjW06igiIhIg/PC0p38e0suft5e/OOWXsSGalCsp1FBERGRBuXrTYd5YelOAKZf34VeLZuanEjOhgqKiIg0GFsP2Znw8QYARl2UyJ96x5ucSM6WCoqIiDQIx4rKGP3uGk5UVHFx20gmX9XB7EhyDlRQRETE45VXOrh73loOFpygVUQTXrqxJz7eeonzZPrTExERjzftyy2sysonyOrDGyN7E9rE1+xIco5UUERExKO9t3If89L3Y7HA7Bu7c15UsNmRxAVUUERExGOl7T7GtC+2APBI/w5c0SHa5ETiKiooIiLikbLzS7hnXvU09gO7x3HXpa3NjiQupIIiIiIep7C0gjvfqZ7GvmvzUP6maewbHJcXlKqqKqZMmUJiYiIBAQG0adOGv/71rxiG4VzHMAymTp1KbGwsAQEBpKamsnPnTldHERGRBqjKYXDf/HVk5hYSFWzltVs1jX1D5PKC8re//Y1XX32Vl156iW3btvG3v/2NmTNn8uKLLzrXmTlzJrNnz2bOnDmkp6cTGBhI//79KS0tdXUcERFpYKZ/tY3vMo9i9fHi9Vt7axr7BsrH1Rv86aefGDhwINdccw0ArVq1Yv78+axatQqoPnsya9Ys/vKXvzBw4EAA3n33XaKjo1m4cCHDhw93dSQREWkg5qXv460fswB47obuJMWHmRtI6ozLz6BccMEFLF26lB07dgCwYcMGfvjhB6666ioAsrKyyMnJITU11fk9oaGhJCcnk5aWdtJtlpWVYbfbazxERKRx+XFXHlM/r75i58E/tOOabrEmJ5K65PIzKJMmTcJut9OhQwe8vb2pqqpi+vTpjBgxAoCcnBwAoqNrXgoWHR3tfO7XZsyYwbRp01wdVUREPMTuo0Xc/X4GVQ6DQd3jGHfFeWZHkjrm8jMoH3/8MfPmzeODDz5g7dq1vPPOOzz77LO88847Z73NyZMnY7PZnI/s7GwXJhYREXd2vLicUXNXYy+tpGdCGE/rip1GweVnUB5++GEmTZrkHEvStWtX9u3bx4wZMxg5ciQxMTEA5ObmEhv739Nzubm5dO/e/aTbtFqtWK1WV0cVERE3V32PnQz2HiuheVgAr93aW1fsNBIuP4NSUlKCl1fNzXp7e+NwOABITEwkJiaGpUuXOp+32+2kp6eTkpLi6jgiIuKhDMNgysLNrNxTfY+dt27rQ2SQ/rPaWLj8DMq1117L9OnTSUhIoHPnzqxbt47nnnuOO+64AwCLxcL48eN58sknadu2LYmJiUyZMoW4uDgGDRrk6jgiIuKh3vg+i4/WZONlgRdv7EH7GN1jpzFxeUF58cUXmTJlCvfccw9HjhwhLi6OP//5z0ydOtW5ziOPPEJxcTFjxoyhoKCAiy66iMWLF+Pv7+/qOCIi4oG+2ZrLU19vA+Av13Ti8g5RJieS+mYx/neKVw9ht9sJDQ3FZrMREhJidhwREXGhrYfsDJ3zEyXlVdyUnMD0QV00KLaBOJPXb92LR0RE3MYReyl3vrOakvIqLjwvgmnXdVY5aaRUUERExC0Ul1VyxzurOWQrpXVkIK/c1Atfb71MNVb6kxcREdP9cgPAzQftRAT6Mff2voQ28TU7lphIBUVERExlGAbTvtzC0u1Hqm8AOLI3CRFNzI4lJlNBERERU735Qxbvpu3DYoFZw7rTM6Gp2ZHEDaigiIiIaRZvzmH6v6ovJ370qo5c1VU3AJRqKigiImKKdfuPM/6jdRgG3HJ+S+68ONHsSOJGVFBERKTe7T9Wwp3vrKG0wsHl7Zvx2LWddDmx1KCCIiIi9cpWUsHtc1dxrLicznEhvHRTT3x0ObH8io4IERGpN2WVVfz5/TXsPlpMbKg/b93Wh0Cry++6Ig2ACoqIiNQLwzCY9M9NzrsTv317H6JDdA82OTkVFBERqRfPf7OTBesO4u1l4ZURPekQo3upye9TQRERkTr34ar9zF66E4Dpg7pwSbtmJicSd6eCIiIidWrptlz+b+FmAMZdfh7D+yaYnEg8gQqKiIjUmXX7jzP2g7VUOQyG9mrBg1e2MzuSeAgVFBERqRN7jhYx6ue5Ti5t14wZg7tqrhOpNRUUERFxuaOFZYx8exX5xeV0axHKKyN64qu5TuQM6GgRERGXKiqr5Pa5q8jOP0HLiCaa60TOigqKiIi4TEWVg3vmrWXzQTsRgX68c3tfIoOsZscSD6SCIiIiLmEYBhP/uZEVO44S4OvNm7f1oVVkoNmxxEOpoIiIiEs8+59MPltbPRHbyyN60D0+zOxI4sFUUERE5Jy9l7aXl7/bDcBT13fhig7RJicST6eCIiIi52Tx5hymfrEFgAdS2zGsjyZik3OngiIiImdt5Z5j3PfhOgwDbuwbz339zjM7kjQQKigiInJWNh+0MfqdNZRXOkjtGM1fB3bRRGziMiooIiJyxvbmFXPb26soLKukb2I4L93UAx9NxCYupKNJRETOyBF7Kbe8lU5eUTkdY0N4Y2Rv/H29zY4lDYwKioiI1JqtpIJb3/rvLLHv3NGHEH9fs2NJA6SCIiIitXKivIpR76xme04hzYKtvHdHMlHB/mbHkgZKBUVERE6rosrB2A/WsmbfcYL9fXj3jr4kRDQxO5Y0YCooIiJySg6HwcRPN/Lt9iNYfbx467Y+dIwNMTuWNHAqKCIi8rsMw2D6v7bx2brqKexfvbknfVqFmx1LGgEVFBER+V2vLNvNmz9kAfDM0G6awl7qjQqKiIic1Afp+3nm35kA/OWajgzu2cLkRNKYqKCIiMhvfLHhEP+3cBMA91zWhjsvbm1yImlsVFBERKSGb7bmMuGj9RgGjEhO4OH+7c2OJI2QCoqIiDj9uCuPez5YS6XD4PoezXV/HTGNCoqIiACQse84o9+tvvnflZ2ieWZoN7y8VE7EHCooIiLClkM2bnt7FSXlVVzcNpIXdfM/MZmOPhGRRm7XkSJufXMVhaWV9G7ZlH/c0gurj27+J+ZSQRERacSy80u4+Y10jhWX06V5CG/d3ocmfj5mxxJRQRERaaxy7aWMeCOdHHspbaOCePeOZN2ZWNyGCoqISCOUX1zOzW+ksz+/hITwJrx/ZzLhgX5mxxJxqpOCcvDgQW6++WYiIiIICAiga9eurFmzxvm8YRhMnTqV2NhYAgICSE1NZefOnXURRUREfsVeWsGtb6Wz80gRMSH+zLszmegQf7NjidTg8oJy/PhxLrzwQnx9ffn666/ZunUrf//732natKlznZkzZzJ79mzmzJlDeno6gYGB9O/fn9LSUlfHERGR/1FcVskdb69m80E74YF+vH9nMvHhTcyOJfIbFsMwDFducNKkSfz44498//33J33eMAzi4uJ48MEHeeihhwCw2WxER0czd+5chg8fftqfYbfbCQ0NxWazERKiW36LiNRGSXklt729mlVZ+QT7+zB/9Pl0aR5qdixpRM7k9dvlZ1C++OILevfuzZ/+9CeioqLo0aMHr7/+uvP5rKwscnJySE1NdS4LDQ0lOTmZtLS0k26zrKwMu91e4yEiIrVXWlHF6HfXsCornyCrD++NSlY5Ebfm8oKyZ88eXn31Vdq2bcu///1v7r77bu677z7eeecdAHJycgCIjq55y+7o6Gjnc782Y8YMQkNDnY/4+HhXxxYRabBKK6oY814GP+46RqCfN+/c0Yfu8WFmxxI5JZcXFIfDQc+ePXnqqafo0aMHY8aMYfTo0cyZM+estzl58mRsNpvzkZ2d7cLEIiINV3mlg7Hz1rJix1ECfL1567Y+9GoZbnYskdNyeUGJjY2lU6dONZZ17NiR/fv3AxATEwNAbm5ujXVyc3Odz/2a1WolJCSkxkNERE6tosrBvfPXsnT7Eaw+Xrw5sjfJrSPMjiVSKy4vKBdeeCGZmZk1lu3YsYOWLVsCkJiYSExMDEuXLnU+b7fbSU9PJyUlxdVxREQapcoqB+M/Ws+/t+Ti5+3F67f25oLzIs2OJVJrLp/P+IEHHuCCCy7gqaee4oYbbmDVqlW89tprvPbaawBYLBbGjx/Pk08+Sdu2bUlMTGTKlCnExcUxaNAgV8cREWl0qhwGD32yga82HsbX28KcW3pySbtmZscSOSMuLyh9+vRhwYIFTJ48mSeeeILExERmzZrFiBEjnOs88sgjFBcXM2bMGAoKCrjoootYvHgx/v6aKEhE5Fw4HAYT/7mRhesP4eNl4eWbenJFh+jTf6OIm3H5PCj1QfOgiIj8lsNh8H8LNzF/VTbeXhZevLEHV3eNNTuWiJOp86CIiEj9czgMpn6xmfmrsvGywHM3JKmciEfTPbVFRDycw2Ew5fPNzEvfj8UCM4cmMbB7c7NjiZwTFRQREQ9W/bbOZuavqi4nzwxNYmivFmbHEjlnKigiIh7K4TB4dMEmPlxd/bbOs39KYnBPlRNpGFRQREQ80C9X63ySceDnMSfdGdRDb+tIw6GCIiLiYap+Lief/lxOnh/WXWNOpMFRQRER8SBVDoOHP93AZ2sP4u1lYdaw7lybFGd2LBGXU0EREfEQv8wQu2BddTmZPbwH13TTpcTSMKmgiIh4gMoqBw9+soHPf54h9sUbe3CV5jmRBkwFRUTEzVVWOXjg4w18uaG6nLx0U08GdDn53d9FGgoVFBERN1Ze6eC++etYvCUHX+/qe+tc2VnlRBo+FRQRETdVWlHF3e9n8F3mUfy8vXhlRE9SO+nGf9I4qKCIiLih4rJKRr+7hp92H8Pf14vXb+3NxW2bmR1LpN6ooIiIuBl7aQW3v72ajH3HCfTz5q3b+pDcOsLsWCL1SgVFRMSNHC8u59a3VrHpoI0Qfx/euaMvPRKamh1LpN6poIiIuImjhWXc8mY623MKCQ/0471RfekcF2p2LBFTqKCIiLiBHFspN72xkj1Hi2kWbOWDO5NpGx1sdiwR06igiIiYLDu/hBFvpLM/v4S4UH/mjT6fxMhAs2OJmEoFRUTERHuOFjHijXQO20pJCG/CB6OTadG0idmxREyngiIiYpIth2yMfGsVeUXltGkWyLw7zycm1N/sWCJuQQVFRMQEq7LyGTV3NYVllXSKDeHdUX2JDLKaHUvEbaigiIjUs++2H+Gu9zMoq3TQt1U4b9zWmxB/X7NjibgVFRQRkXr0+fqDPPjxBiodBld0iOLlm3oS4OdtdiwRt6OCIiJST95L28vUL7ZgGDCwexzP/ikJX28vs2OJuCUVFBGROmYYBi99u4u/L9kBwMiUljx2bWe8vCwmJxNxXyooIiJ1yOEwePKrbbz1YxYA9/VrywOpbbFYVE5ETkUFRUSkjlRWOZj02SY+zTgAwJQ/dmLURYkmpxLxDCooIiJ1oLSiivvmr+M/W3Px9rIwc0g3hvRqYXYsEY+hgiIi4mK2kgrufHc1q/cex8/Hi5dv6skfOkWbHUvEo6igiIi40KGCE9z29ip25BYRbPXhtVt7k9ImwuxYIh5HBUVExEV25BZy65uryLGXEh1iZe7tfekYG2J2LBGPpIIiIuICq7LyufOd1dhLK2nTLJB3RyXTPCzA7FgiHksFRUTkHC3efJj7PlxPeaWDXi2b8satvWka6Gd2LBGPpoIiInIO3lu5j6mfb8YwILVjNC/d1AN/X01dL3KuVFBERM6CYRg8t2QHL367C4Ab+ybw14Gd8dHU9SIuoYIiInKGKqscPLpgEx+vqZ6AbXxqW+7vp9lhRVxJBUVE5AwUlVUy7oO1LMs8ipcFpl/flRv7JpgdS6TBUUEREamlHFspd8xdzdbDdvx9vZg9vAdXdo4xO5ZIg6SCIiJSC9sO27n97dXk2EuJDPLjjZF96B4fZnYskQZLBUVE5DSW7zjK2HlrKSqrnuNk7u19iQ9vYnYskQZNBUVE5BTmr9rPXxZupsphcH7rcP5xc29Cm/iaHUukwVNBERE5CYfD4Jn/ZPLqst0ADO7RnKeHdMPPR5cRi9SHOv+b9vTTT2OxWBg/frxzWWlpKWPHjiUiIoKgoCCGDBlCbm5uXUcREamV0ooq7vtwnbOc3N+vLX+/IUnlRKQe1enfttWrV/OPf/yDbt261Vj+wAMP8OWXX/LJJ5+wfPlyDh06xODBg+syiohIreQXl3PzG+ks2ngYHy8Lz/4piQf+0E5znIjUszorKEVFRYwYMYLXX3+dpk2bOpfbbDbefPNNnnvuOa644gp69erF22+/zU8//cTKlSvrKo6IyGntPlrEkFd/Ys2+4wT7+/DuHX0Z2quF2bFEGqU6Kyhjx47lmmuuITU1tcbyjIwMKioqaizv0KEDCQkJpKWl1VUcEZFT+n7nUa5/+Uey8oppHhbAZ3dfwAXnRZodS6TRqpNBsh9++CFr165l9erVv3kuJycHPz8/wsLCaiyPjo4mJyfnpNsrKyujrKzM+bXdbndpXhFp3N5L28vjX26lymHQq2VT5tzci2bBVrNjiTRqLi8o2dnZ3H///SxZsgR/f3+XbHPGjBlMmzbNJdsSEflFZZWDJxZt5d20fUD1lTpPDe6quxGLuAGXv8WTkZHBkSNH6NmzJz4+Pvj4+LB8+XJmz56Nj48P0dHRlJeXU1BQUOP7cnNziYk5+ZTRkydPxmazOR/Z2dmuji0ijYytpILb3l7Nu2n7sFhg4oAO/P2GJJUTETfh8jMo/fr1Y9OmTTWW3X777XTo0IGJEycSHx+Pr68vS5cuZciQIQBkZmayf/9+UlJSTrpNq9WK1arTrSLiGll5xYyau5o9ecU08fNm1rDuuqeOiJtxeUEJDg6mS5cuNZYFBgYSERHhXD5q1CgmTJhAeHg4ISEh3HvvvaSkpHD++ee7Oo6ISA0/7crj7nlrsZ2ooHlYAK/f2ptOcSFmxxKRXzFlJtnnn38eLy8vhgwZQllZGf379+eVV14xI4qINCLz0vcx9fMtVDkMeiaE8Y9bemswrIibshiGYZgd4kzZ7XZCQ0Ox2WyEhOh/PiJyahVVDv76P4Nhr+/RnBkaDCtS787k9Vv34hGRBi2vqIx73l/Lqr35WCzw0JXtueeyNpoZVsTNqaCISIO18UABf34vg8O2UoKtPswa3p1+HaPNjiUitaCCIiIN0j8zDjB5wSbKKx20aRbIa7f2pk2zILNjiUgtqaCISINSUeXgqX9t4+0f9wKQ2jGa54clEezva24wETkjKigi0mAcKypj7AdrWbknH4D7+7Xl/n5t8fLSeBMRT6OCIiINwuaDNv78XgYHC04Q6OfNc8O601+Tr4l4LBUUEfF4n68/yMR/bqS0wkFiZCCv3dKLttHBZscSkXOggiIiHqu80sH0r7byzs/zm1zWvhkvDO9BaIDGm4h4OhUUEfFIhwpOMPaDtazbXwDAuMvP44E/tMNb401EGgQVFBHxOD/szOO+D9eRX1xOiL8Pzw/T/CYiDY0Kioh4DIfD4JVlu/j7kh0YBnSOC+HVEb1IiGhidjQRcTEVFBHxCLaSCh74eD3fbj8CwLDe8Uwb2Fn30xFpoFRQRMTtbT5o4673Mzhw/ARWHy/+OrALN/SJNzuWiNQhFRQRcVuGYfDR6mymfrGF8koHCeFNeGVET7o0DzU7mojUMRUUEXFLRWWV/GXBJhauPwRAasco/v6n7oQ20SXEIo2BCoqIuJ0th2yM+2AdWXnFeHtZePDKdtx1SRtNWS/SiKigiIjbMAyD91fu469fbaO80kFsqD8v3tiD3q3CzY4mIvVMBUVE3ILtRAWTP9vIvzblANCvQxTP/imJpoF+JicTETOooIiI6TZkFzBu/lqy80/g621h4oAOjLooEYtFb+mINFYqKCJiGsMwePOHLP62eDsVVQbx4QG8eGNPuseHmR1NREymgiIipjhWVMYjn25k6c8Tr13VJYanh3TTjf5EBFBBERETrNhxlAc/2cDRwjL8vL2Y8seO3Hx+S72lIyJOKigiUm/KKquYuTiTN3/IAuC8qCBeGN6dznGaeE1EalJBEZF6sSO3kPvmr2N7TiEAt5zfkkev7kiAn+6lIyK/pYIiInXKMAzeW7mP6V9to6zSQXigHzOHdCO1U7TZ0UTEjamgiEidyft5IOwvdyC+uG0kf/9TElEh/iYnExF3p4IiInViWeYRHvpkI3lF1QNhJ17VgdsvaKXp6kWkVlRQRMSlissqmfH1Nt5fuR+AtlFBzL6xBx1jQ0xOJiKeRAVFRFxm9d58HvpkA/uOlQAwMqUlk6/uiL+vBsKKyJlRQRGRc1ZaUcXzS3bw2vd7MAyIC/Vn5tAkLmobaXY0EfFQKigick42H7Qx4eP17MgtAmBIzxY8dl0nQvw1I6yInD0VFBE5K5VVDl5ZtpvZS3dS6TCIDPJj+vVd6d85xuxoItIAqKCIyBnbdaSIBz9ez4YDNgAGdI5h+vVdiAiympxMRBoKFRQRqbXKKgdv/JDF80t2UFbpIMTfhycGdmFg9zjdR0dEXEoFRURqZXuOnUc+3cjGn8+aXNw2kplDuxEbGmByMhFpiFRQROSUyisdvPzdLl5ZtouKKoMQfx/+8sdO/KlXC501EZE6o4IiIr9rQ3YBE/+50XmDvz90iubJQV2I1lT1IlLHVFBE5Dd+mdfk9e/34DAgPNCPadd15o/dYnXWRETqhQqKiNSwKiufif/cSFZeMQDXJcXx2LWddIWOiNQrFRQRAcBWUsHTi7cxf1U2ANEhVqYP6kpqp2iTk4lIY6SCItLIGYbBFxsO8ddFW8krKgdgWO94Hr2mI6EBmg1WRMyhgiLSiO3NK+YvCzfzw648AM6LCmL6oC4kt44wOZmINHYqKCKNUHmlg38s382L3+2ivNKBn48X911xHmMuaYOfj5fZ8UREcPm/RDNmzKBPnz4EBwcTFRXFoEGDyMzMrLFOaWkpY8eOJSIigqCgIIYMGUJubq6ro4jISaTvOcbVs7/n70t2UF7p4OK2kfxn/CWMu6KtyomIuA2X/2u0fPlyxo4dy8qVK1myZAkVFRVceeWVFBcXO9d54IEH+PLLL/nkk09Yvnw5hw4dYvDgwa6OIiL/41hRGY98uoFhr61k15EiIoP8eGF4d969oy+tIgPNjiciUoPFMAyjLn/A0aNHiYqKYvny5VxyySXYbDaaNWvGBx98wNChQwHYvn07HTt2JC0tjfPPP/+027Tb7YSGhmKz2QgJCanL+CIer7LKwQer9vPsvzOxl1YCcGPfBCYN6EBoEw2CFZH6cyav33U+BsVmq75vR3h4OAAZGRlUVFSQmprqXKdDhw4kJCTUuqCISO2s3pvP1M+3sO2wHYCOsSH8dWBnercKNzmZiMip1WlBcTgcjB8/ngsvvJAuXboAkJOTg5+fH2FhYTXWjY6OJicn56TbKSsro6yszPm13W6vs8wiDcEReykzvt7OgnUHAQjx9+Hh/u25Kbkl3l6aCVZE3F+dFpSxY8eyefNmfvjhh3PazowZM5g2bZqLUok0XBVVDub+uJcXlu6kqKwSiwWG94nnoSvbayZYEfEodVZQxo0bx6JFi1ixYgUtWrRwLo+JiaG8vJyCgoIaZ1Fyc3OJiYk56bYmT57MhAkTnF/b7Xbi4+PrKrqIR/pxVx6PfbGFXUeKAEiKD+OJ6zqTFB9mbjARkbPg8oJiGAb33nsvCxYsYNmyZSQmJtZ4vlevXvj6+rJ06VKGDBkCQGZmJvv37yclJeWk27RarVit+t+fyMnsOVrEU//azjfbqi/Vjwj0Y+KADgzt1QIvvZ0jIh7K5QVl7NixfPDBB3z++ecEBwc7x5WEhoYSEBBAaGgoo0aNYsKECYSHhxMSEsK9995LSkqKBsiKnIGCknJeWLqT99L2Uekw8PaycMv5LXkgtZ2uzhERj+fyy4x/71bsb7/9NrfddhtQPVHbgw8+yPz58ykrK6N///688sorv/sWz6/pMmNpzCqqHLy/ch+zvtmJ7UQFAJe3b8b/XdOR86KCTU4nIvL7zuT1u87nQakLKijSGBmGwdJtR3jqX9vYk1c98WH76GD+75qOXNKumcnpREROz63mQRGRc7flkI3pX23jp93HAIgM8mPCH9pzQ+8W+HhrenoRaXhUUETcWHZ+CX//TyYL1x8CwM/Hi1EXJXLPZW0I9tc4ExFpuFRQRNxQXlEZL327i3np+6ioqn4X9tqkOB7p35748CYmpxMRqXsqKCJupKiskje+38PrK/ZQXF4FwMVtI5k4oANdmoeanE5EpP6ooIi4gfJKB/NX7Wf20p0cKy4HoGvzUCZd1YELz4s0OZ2ISP1TQRExUWWVg8/XH+KFpTvZn18CQKuIJjzUvz1Xd4nVRGsi0mipoIiYoMphsGjjIV74ZqfzkuHIICvjU9syrE88vroyR0QaORUUkXrkcBj8a/NhZn2z03nPnKZNfBlzSRtGXtCSJn76KykiAiooIvXC4TD4z9Ycnl+yk8zcQgBCA3wZc0lrRl7QiiCr/iqKiPwv/asoUoccDoNvtuUy65udbD1sByDY6sOoixO546JEQjSXiYjISamgiNSBX8aYvPLdbucZk0A/b+64KJE7L2qtm/mJiJyGCoqIC5VXOvhs7QHmLN/N3mPVV+UEWX24JaUlYy5uTdNAP5MTioh4BhUUERc4UV7Fh6v389qKPRy2lQIQ1sSXOy5MZGRKK50xERE5QyooIufAXlrB+yv38eb3Wc4J1qKCrYy5pDU39k0gUINfRUTOiv71FDkLB46X8PaPe/lodTZFZZUAxIcHcNelbRjSswX+vt4mJxQR8WwqKCJnYOOBAl7/Pot/bTpMlaP6Jn7tooO469I2XJcUh48mWBMRcQkVFJHTcDgMvss8wmsr9pCele9cfuF5EYy+uDWXtmuGxaIp6UVEXEkFReR3nCivYsG6g7z5wx52H62ejt7Hy8K1SXHceXEineN0d2ERkbqigiLyK/uPlfDeyurxJfbS6vElwVYfbkpO4LYLWxEbGmByQhGRhk8FRYTqt3G+35XHOz/t5bvMIxjVw0uIDw9gZEorhvWJJ1izvoqI1BsVFGnU7KUVfLrmAO+t3EfWz3cVBrikXTNuu6All7aLwttL40tEROqbCoo0OoZhsPGAjQ9XZ/P5+oOUlFcB1W/jDO3dglvOb0nrZkEmpxQRadxUUKTRsJdW8Pm6g3ywKpttP9+4D6BtVBC3XtCKwT2aa2I1ERE3oX+NpUEzDIOMfceZvyqbrzYdorTCAYCfjxdXdYlheJ8Ezm8drsuERUTcjAqKNEhHC8v4fP1BPlydza4jRc7l7aKDGN4ngcE9mxPWRDfuExFxVyoo0mCUVlSxZGsun609wIqdec6ZXgN8vbk2KZZhfRLomRCmsyUiIh5ABUU8msNhsHpvPp+tPci/Nh2m8Of74gB0jw9jaK8WDOwep0uERUQ8jAqKeKRdR4r4fP1BFqw7yIHjJ5zLm4cFMLhnc67v0VxX4oiIeDAVFPEYe/OKWbTxEIs2HmZ7TqFzeZDVh6u7xjC4Zwv6tgrHS/OWiIh4PBUUcWvZ+SUs2niYrzYdYvPB/14a7ONl4aK2kQzu2YI/dIwmwM/bxJQiIuJqKijidvYfK+HfW3JYtPEQGw7YnMu9vSxc0CaCP3aL5cpOMTQN1FU4IiINlQqKmO6XmV2XbM1lydZcMnP/+/aNlwWSEyP4Y1IsAzrHEBFkNTGpiIjUFxUUMUV5pYO0PcdYsjWHb7YeIcde6nzO28tCn1ZNubprLAO6xBAV7G9iUhERMYMKitSbXHspy3ccZXnmUVbsOFrjkuAmft5c2q4Zf+gUzRUdojSJmohII6eCInWmvNLBmn35zlLyv1feADQLtpLaMZorO0WT0iYCf18NdBURkWoqKOIyhmGw+2gxabvzWLEzj5925VH8852CASwW6NYijEvbNeOy9s3o3iJMlwSLiMhJqaDIWTMMg/35JaTtPkbanmOk7T7GkcKyGutEBvlxSbtmXNquGRe3bUa4rrwREZFaUEGRWjMMg33HSliz7zhpu4+xcs8xDhacqLGOn48XvRKacuF5EVzWPopOsSE6SyIiImdMBUV+V2lFFZsP2sjYd5w1+46zdt9xjhWX11jHx8tCj4QwUlpHkNImkh4JYRpLIiIi50wFRYD/nh3ZdNDGxgMFZOw7zuaDdsqrHDXW8/P2omuLUPq0CueCNhH0btWUJn46jERExLX0ytIIGYZBdv6J6jJysIBNB2xsPmjDXlr5m3Ujg/zomdCU3q2a0qtlUzrHheoMiYiI1DkVlAausLSCHbmFbM8pZEdO9cftOYXYTlT8Zl0/by86xgbTpXkoPROqC0nLiCZYLBpDIiIi9UsFpQEwDIPjJRVk5RWRlVfC7qNFZOYUkplT+JtBrL/w8/aiw89lpFvzULo0D6VddDB+Pl71nF5EROS3TC0oL7/8Ms888ww5OTkkJSXx4osv0rdvXzMjuS3DMMgrKudgwQmy80vIyitmb14xe/KKycorPukZkV/EhPjTPiaYDjHBtIsOpv3PH1VGRETEXZlWUD766CMmTJjAnDlzSE5OZtasWfTv35/MzEyioqLMimUKwzCwnajgaGEZRwvLyLGXcvD4CQ4W/Pz4+fOySscpt9M8LIBWkU1IjAykfXQw7WNCaB8dTGgT33r6TURERFzDYhiGYcYPTk5Opk+fPrz00ksAOBwO4uPjuffee5k0adIpv9dutxMaGorNZiMkJKQ+4taaYRiUlFdhO1FBQUkFthPVD/uJ/35+rLi8uowUlZH3cyn59dUyJ2OxQFSwlRZNq0tIYmQgrSMDSWwWSMvwQAL8NHhVRETc15m8fptyBqW8vJyMjAwmT57sXObl5UVqaippaWm/Wb+srIyysv/OUGq32+sk15q9+SzaeBiHYVDpMHA4DKp+efzPstKKKk5UVHGiwsGJ8srqz8v/+7njLCtfiL8PzYKtRIf40zwsgOZNA6o//vx5bGiA3pYREZFGwZSCkpeXR1VVFdHR0TWWR0dHs3379t+sP2PGDKZNm1bnuTJzC5n7016XbMvX20JogC8hAb6E/vwI++VjEz+iQqw0C7LSLLj6ERlk1eW7IiIiP/OIq3gmT57MhAkTnF/b7Xbi4+Nd/nM6x4Vyz2Vt8PGy4OVlqfnRUv3R28uC1debgJ8fTfy88ff779cBft4E+/sQ4Outy3NFRETOkikFJTIyEm9vb3Jzc2ssz83NJSYm5jfrW61WrFZrnefqHh9G9/iwOv85IiIicmqmDGjw8/OjV69eLF261LnM4XCwdOlSUlJSzIgkIiIibsS0t3gmTJjAyJEj6d27N3379mXWrFkUFxdz++23mxVJRERE3IRpBWXYsGEcPXqUqVOnkpOTQ/fu3Vm8ePFvBs6KiIhI42PaPCjnwp3nQREREZGTO5PXb02qISIiIm5HBUVERETcjgqKiIiIuB0VFBEREXE7KigiIiLidlRQRERExO2ooIiIiIjbUUERERERt6OCIiIiIm7HtKnuz8Uvk9/a7XaTk4iIiEht/fK6XZtJ7D2yoBQWFgIQHx9vchIRERE5U4WFhYSGhp5yHY+8F4/D4eDQoUMEBwdjsVhcum273U58fDzZ2dm6z89paF/VnvZV7Wlf1Z72Ve1pX52ZutpfhmFQWFhIXFwcXl6nHmXikWdQvLy8aNGiRZ3+jJCQEB3EtaR9VXvaV7WnfVV72le1p311Zupif53uzMkvNEhWRERE3I4KioiIiLgdFZRfsVqtPPbYY1itVrOjuD3tq9rTvqo97ava076qPe2rM+MO+8sjB8mKiIhIw6YzKCIiIuJ2VFBERETE7aigiIiIiNtRQRERERG3o4LyP15++WVatWqFv78/ycnJrFq1yuxIbufxxx/HYrHUeHTo0MHsWG5jxYoVXHvttcTFxWGxWFi4cGGN5w3DYOrUqcTGxhIQEEBqaio7d+40J6zJTrevbrvttt8cawMGDDAnrIlmzJhBnz59CA4OJioqikGDBpGZmVljndLSUsaOHUtERARBQUEMGTKE3NxckxKbqzb767LLLvvNsXXXXXeZlNg8r776Kt26dXNOxpaSksLXX3/tfN7s40oF5WcfffQREyZM4LHHHmPt2rUkJSXRv39/jhw5YnY0t9O5c2cOHz7sfPzwww9mR3IbxcXFJCUl8fLLL5/0+ZkzZzJ79mzmzJlDeno6gYGB9O/fn9LS0npOar7T7SuAAQMG1DjW5s+fX48J3cPy5csZO3YsK1euZMmSJVRUVHDllVdSXFzsXOeBBx7gyy+/5JNPPmH58uUcOnSIwYMHm5jaPLXZXwCjR4+ucWzNnDnTpMTmadGiBU8//TQZGRmsWbOGK664goEDB7JlyxbADY4rQwzDMIy+ffsaY8eOdX5dVVVlxMXFGTNmzDAxlft57LHHjKSkJLNjeATAWLBggfNrh8NhxMTEGM8884xzWUFBgWG1Wo358+ebkNB9/HpfGYZhjBw50hg4cKApedzZkSNHDMBYvny5YRjVx5Cvr6/xySefONfZtm2bARhpaWlmxXQbv95fhmEYl156qXH//febF8qNNW3a1HjjjTfc4rjSGRSgvLycjIwMUlNTncu8vLxITU0lLS3NxGTuaefOncTFxdG6dWtGjBjB/v37zY7kEbKyssjJyalxnIWGhpKcnKzj7HcsW7aMqKgo2rdvz913382xY8fMjmQ6m80GQHh4OAAZGRlUVFTUOK46dOhAQkKCjit+u79+MW/ePCIjI+nSpQuTJ0+mpKTEjHhuo6qqig8//JDi4mJSUlLc4rjyyJsFulpeXh5VVVVER0fXWB4dHc327dtNSuWekpOTmTt3Lu3bt+fw4cNMmzaNiy++mM2bNxMcHGx2PLeWk5MDcNLj7Jfn5L8GDBjA4MGDSUxMZPfu3Tz66KNcddVVpKWl4e3tbXY8UzgcDsaPH8+FF15Ily5dgOrjys/Pj7CwsBrr6rg6+f4CuOmmm2jZsiVxcXFs3LiRiRMnkpmZyWeffWZiWnNs2rSJlJQUSktLCQoKYsGCBXTq1In169ebflypoMgZueqqq5yfd+vWjeTkZFq2bMnHH3/MqFGjTEwmDc3w4cOdn3ft2pVu3brRpk0bli1bRr9+/UxMZp6xY8eyefNmjfuqpd/bX2PGjHF+3rVrV2JjY+nXrx+7d++mTZs29R3TVO3bt2f9+vXYbDY+/fRTRo4cyfLly82OBWiQLACRkZF4e3v/ZnRybm4uMTExJqXyDGFhYbRr145du3aZHcXt/XIs6Tg7O61btyYyMrLRHmvjxo1j0aJFfPfdd7Ro0cK5PCYmhvLycgoKCmqs39iPq9/bXyeTnJwM0CiPLT8/P8477zx69erFjBkzSEpK4oUXXnCL40oFheo/oF69erF06VLnMofDwdKlS0lJSTExmfsrKipi9+7dxMbGmh3F7SUmJhITE1PjOLPb7aSnp+s4q4UDBw5w7NixRnesGYbBuHHjWLBgAd9++y2JiYk1nu/Vqxe+vr41jqvMzEz279/fKI+r0+2vk1m/fj1Aozu2TsbhcFBWVuYex1W9DMX1AB9++KFhtVqNuXPnGlu3bjXGjBljhIWFGTk5OWZHcysPPvigsWzZMiMrK8v48ccfjdTUVCMyMtI4cuSI2dHcQmFhobFu3Tpj3bp1BmA899xzxrp164x9+/YZhmEYTz/9tBEWFmZ8/vnnxsaNG42BAwcaiYmJxokTJ0xOXv9Ota8KCwuNhx56yEhLSzOysrKMb775xujZs6fRtm1bo7S01Ozo9eruu+82QkNDjWXLlhmHDx92PkpKSpzr3HXXXUZCQoLx7bffGmvWrDFSUlKMlJQUE1Ob53T7a9euXcYTTzxhrFmzxsjKyjI+//xzo3Xr1sYll1xicvL6N2nSJGP58uVGVlaWsXHjRmPSpEmGxWIx/vOf/xiGYf5xpYLyP1588UUjISHB8PPzM/r27WusXLnS7EhuZ9iwYUZsbKzh5+dnNG/e3Bg2bJixa9cus2O5je+++84AfvMYOXKkYRjVlxpPmTLFiI6ONqxWq9GvXz8jMzPT3NAmOdW+KikpMa688kqjWbNmhq+vr9GyZUtj9OjRjfI/DCfbR4Dx9ttvO9c5ceKEcc899xhNmzY1mjRpYlx//fXG4cOHzQttotPtr/379xuXXHKJER4eblitVuO8884zHn74YcNms5kb3AR33HGH0bJlS8PPz89o1qyZ0a9fP2c5MQzzjyuLYRhG/ZyrEREREakdjUERERERt6OCIiIiIm5HBUVERETcjgqKiIiIuB0VFBEREXE7KigiIiLidlRQRERExO2ooIiIiIjbUUERERERt6OCIiIiIm5HBUVERETcjgqKiIiIuJ3/B0IWL2+dZGlvAAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(x, dragf)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "%run ../src/solarcarsim/noise.py"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "key = random.key(123)\n",
    "fractal_tex = generate_noise_texture(key, 256, 256, \"fractal\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x7101a4373b30>"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.imshow(fractal_tex)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pyvista as pv\n",
    "import numpy as np\n",
    "a = np.array(fractal_tex)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/saji/Documents/Code/solarcarsim/.venv/lib/python3.12/site-packages/pyvista/plotting/texture.py:682: UserWarning: Expected `image` dtype to be ``np.uint8``. `image` has been copied and converted to np.uint8.\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "tex = pv.numpy_to_texture(a)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/saji/Documents/Code/solarcarsim/.venv/lib/python3.12/site-packages/pyvista/core/utilities/points.py:55: UserWarning: Points is not a float type. This can cause issues when transforming or applying filters. Casting to ``np.float32``. Disable this by passing ``force_float=False``.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "x = np.arange(0,256)\n",
    "y = np.arange(0,256)\n",
    "x, y = np.meshgrid(x, y)\n",
    "fig, ax = plt.subplots(subplot_kw={\"projection\": \"3d\"})\n",
    "ax.plot_surface(x,y,a)\n",
    "grid=pv.StructuredGrid(x,y, a * 100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x7100e506cf80>]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "key = random.key(123)\n",
    "key, subkey = random.split(key)\n",
    "y = generate_elevation_profile(subkey, 100, scale=100)\n",
    "plt.plot(y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x7100e4f72db0>"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "key, subkey = random.split(key)\n",
    "y = generate_wind_field(subkey, 100, 100)\n",
    "plt.imshow(y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x400 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%run ../src/solarcarsim/physsim.py\n",
    "from jax import random\n",
    "import matplotlib.pyplot as plt\n",
    "plt.rcParams.update({\n",
    "    \"text.usetex\": True,\n",
    "})\n",
    "wind, elevation, slope = make_environment(random.key(123))\n",
    "fig, (ax1, ax2) = plt.subplots(1,2, figsize=(10,4))\n",
    "fig.set_tight_layout('auto')\n",
    "fig.suptitle(\"Generated Environment\")\n",
    "\n",
    "ax1.imshow(wind, aspect='auto')\n",
    "ax1.set_title(\"Wind Map\")\n",
    "ax1.set_ylabel(\"Time (sec)\")\n",
    "ax1.set_xlabel(\"Distance (m)\")\n",
    "\n",
    "\n",
    "ax2.set_title(\"Terrain\")\n",
    "ax_slope = ax2.twinx()\n",
    "\n",
    "ax2.plot(elevation, label=\"Elevation\")\n",
    "ax2.set_ylabel(\"Elevation (m)\")\n",
    "ax2.set_xlabel(\"Distance (m)\")\n",
    "ax_slope.plot(slope, color='r', label='Slope')\n",
    "ax_slope.set_ylabel(\"Slope (rad)\")\n",
    "ax2.legend(loc=2)\n",
    "ax_slope.legend(loc=1)\n",
    "fig.savefig(\"environment.pdf\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x7100e4dcb050>"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# testing the indexing into the wind array.\n",
    "ax2.legend()\n",
    "# given an array of shape (10,2)\n",
    "# return an array of (10,100,100)\n",
    "key = random.key(0)\n",
    "@jit\n",
    "def lookup(x):\n",
    "    return lax.dynamic_slice(wind, x, (100, 100))\n",
    "vlookup = vmap(lookup)\n",
    "res = vlookup(jnp.array([[10,20], [9999, 600]]))\n",
    "\n",
    "fig, (ax1, ax2) = plt.subplots(1,2)\n",
    "ax1.imshow(res[0])\n",
    "ax2.imshow(res[1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%run ../src/solarcarsim/simv1.py\n",
    "import gymnasium as gym\n",
    "from gymnasium.wrappers.jax_to_numpy import JaxToNumpy\n",
    "from gymnasium.wrappers.vector import JaxToNumpy as VJaxToNumpy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/saji/Documents/Code/solarcarsim/.venv/lib/python3.12/site-packages/stable_baselines3/common/env_checker.py:271: UserWarning: Your observation wind has an unconventional shape (neither an image, nor a 1D vector). We recommend you to flatten the observation to have only a 1D vector or use a custom policy to properly process the data.\n",
      "  warnings.warn(\n",
      "/home/saji/Documents/Code/solarcarsim/.venv/lib/python3.12/site-packages/gymnasium/utils/env_checker.py:384: UserWarning: \u001b[33mWARN: The environment (<JaxToNumpy<SolarRaceV1 instance>>) is different from the unwrapped version (<SolarRaceV1 instance>). This could effect the environment checker as the environment most likely has a wrapper applied to it. We recommend using the raw environment for `check_env` using `env.unwrapped`.\u001b[0m\n",
      "  logger.warn(\n",
      "/home/saji/Documents/Code/solarcarsim/.venv/lib/python3.12/site-packages/gymnasium/utils/env_checker.py:434: UserWarning: \u001b[33mWARN: Not able to test alternative render modes due to the environment not having a spec. Try instantiating the environment through `gymnasium.make`\u001b[0m\n",
      "  logger.warn(\n"
     ]
    }
   ],
   "source": [
    "env = SolarRaceV1()\n",
    "wrapped_env = JaxToNumpy(env)\n",
    "env.reset()\n",
    "from stable_baselines3.common.env_checker import check_env\n",
    "from gymnasium.utils.env_checker import check_env as gym_check_env\n",
    "check_env(wrapped_env)\n",
    "gym_check_env(wrapped_env)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Using cuda device\n",
      "Wrapping the env with a `Monitor` wrapper\n",
      "Wrapping the env in a DummyVecEnv.\n",
      "---------------------------------\n",
      "| rollout/           |          |\n",
      "|    ep_len_mean     | 601      |\n",
      "|    ep_rew_mean     | 8.77e+11 |\n",
      "| time/              |          |\n",
      "|    fps             | 335      |\n",
      "|    iterations      | 1        |\n",
      "|    time_elapsed    | 6        |\n",
      "|    total_timesteps | 2048     |\n",
      "---------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.72e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 313      |\n",
      "|    iterations           | 2        |\n",
      "|    time_elapsed         | 13       |\n",
      "|    total_timesteps      | 4096     |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 2.52e+20 |\n",
      "|    n_updates            | 10       |\n",
      "|    policy_gradient_loss | 6.05e-10 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 6.84e+20 |\n",
      "--------------------------------------\n",
      "--------------------------------------------\n",
      "| rollout/                |                |\n",
      "|    ep_len_mean          | 601            |\n",
      "|    ep_rew_mean          | 8.55e+11       |\n",
      "| time/                   |                |\n",
      "|    fps                  | 309            |\n",
      "|    iterations           | 3              |\n",
      "|    time_elapsed         | 19             |\n",
      "|    total_timesteps      | 6144           |\n",
      "| train/                  |                |\n",
      "|    approx_kl            | -2.0372681e-10 |\n",
      "|    clip_fraction        | 0              |\n",
      "|    clip_range           | 0.2            |\n",
      "|    entropy_loss         | -1.42          |\n",
      "|    explained_variance   | 0              |\n",
      "|    learning_rate        | 0.0003         |\n",
      "|    loss                 | 3.5e+20        |\n",
      "|    n_updates            | 20             |\n",
      "|    policy_gradient_loss | -2.82e-10      |\n",
      "|    std                  | 1              |\n",
      "|    value_loss           | 7.52e+20       |\n",
      "--------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.65e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 309          |\n",
      "|    iterations           | 4            |\n",
      "|    time_elapsed         | 26           |\n",
      "|    total_timesteps      | 8192         |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 4.23e+20     |\n",
      "|    n_updates            | 30           |\n",
      "|    policy_gradient_loss | -6.43e-10    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 6.91e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.61e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 309       |\n",
      "|    iterations           | 5         |\n",
      "|    time_elapsed         | 33        |\n",
      "|    total_timesteps      | 10240     |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.09e+20  |\n",
      "|    n_updates            | 40        |\n",
      "|    policy_gradient_loss | -1.82e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.55e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------------\n",
      "| rollout/                |                |\n",
      "|    ep_len_mean          | 601            |\n",
      "|    ep_rew_mean          | 8.64e+11       |\n",
      "| time/                   |                |\n",
      "|    fps                  | 309            |\n",
      "|    iterations           | 6              |\n",
      "|    time_elapsed         | 39             |\n",
      "|    total_timesteps      | 12288          |\n",
      "| train/                  |                |\n",
      "|    approx_kl            | -1.1641532e-10 |\n",
      "|    clip_fraction        | 0              |\n",
      "|    clip_range           | 0.2            |\n",
      "|    entropy_loss         | -1.42          |\n",
      "|    explained_variance   | 0              |\n",
      "|    learning_rate        | 0.0003         |\n",
      "|    loss                 | 3.86e+20       |\n",
      "|    n_updates            | 50             |\n",
      "|    policy_gradient_loss | 7.23e-09       |\n",
      "|    std                  | 1              |\n",
      "|    value_loss           | 7.96e+20       |\n",
      "--------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.63e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 7            |\n",
      "|    time_elapsed         | 46           |\n",
      "|    total_timesteps      | 14336        |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 5.820766e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.05e+20     |\n",
      "|    n_updates            | 60           |\n",
      "|    policy_gradient_loss | -6.76e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.04e+20     |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.6e+11       |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 8             |\n",
      "|    time_elapsed         | 53            |\n",
      "|    total_timesteps      | 16384         |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.27e+20      |\n",
      "|    n_updates            | 70            |\n",
      "|    policy_gradient_loss | 6.42e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.66e+20      |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.65e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 9         |\n",
      "|    time_elapsed         | 59        |\n",
      "|    total_timesteps      | 18432     |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.38e+20  |\n",
      "|    n_updates            | 80        |\n",
      "|    policy_gradient_loss | -2.08e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.94e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.63e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 10        |\n",
      "|    time_elapsed         | 66        |\n",
      "|    total_timesteps      | 20480     |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.77e+20  |\n",
      "|    n_updates            | 90        |\n",
      "|    policy_gradient_loss | -4.44e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.87e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.64e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 11            |\n",
      "|    time_elapsed         | 73            |\n",
      "|    total_timesteps      | 22528         |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.84e+20      |\n",
      "|    n_updates            | 100           |\n",
      "|    policy_gradient_loss | -3.09e-10     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.7e+20       |\n",
      "-------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.65e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 12       |\n",
      "|    time_elapsed         | 79       |\n",
      "|    total_timesteps      | 24576    |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.47e+20 |\n",
      "|    n_updates            | 110      |\n",
      "|    policy_gradient_loss | 5.43e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.17e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.63e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 13        |\n",
      "|    time_elapsed         | 86        |\n",
      "|    total_timesteps      | 26624     |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.95e+20  |\n",
      "|    n_updates            | 120       |\n",
      "|    policy_gradient_loss | -4.86e-10 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.55e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.62e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 14       |\n",
      "|    time_elapsed         | 92       |\n",
      "|    total_timesteps      | 28672    |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.6e+20  |\n",
      "|    n_updates            | 130      |\n",
      "|    policy_gradient_loss | 4.9e-09  |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.01e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.62e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 15        |\n",
      "|    time_elapsed         | 99        |\n",
      "|    total_timesteps      | 30720     |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.84e+20  |\n",
      "|    n_updates            | 140       |\n",
      "|    policy_gradient_loss | -7.74e-10 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.1e+20   |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.6e+11   |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 16        |\n",
      "|    time_elapsed         | 106       |\n",
      "|    total_timesteps      | 32768     |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.22e+20  |\n",
      "|    n_updates            | 150       |\n",
      "|    policy_gradient_loss | -2.27e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.73e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.6e+11   |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 17        |\n",
      "|    time_elapsed         | 112       |\n",
      "|    total_timesteps      | 34816     |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 2.86e+20  |\n",
      "|    n_updates            | 160       |\n",
      "|    policy_gradient_loss | -6.14e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.47e+20  |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.6e+11      |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 18           |\n",
      "|    time_elapsed         | 119          |\n",
      "|    total_timesteps      | 36864        |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 4.05e+20     |\n",
      "|    n_updates            | 170          |\n",
      "|    policy_gradient_loss | 2.55e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.59e+20     |\n",
      "------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.6e+11  |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 19       |\n",
      "|    time_elapsed         | 126      |\n",
      "|    total_timesteps      | 38912    |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.49e+20 |\n",
      "|    n_updates            | 180      |\n",
      "|    policy_gradient_loss | 3.69e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 6.98e+20 |\n",
      "--------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.61e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 20       |\n",
      "|    time_elapsed         | 132      |\n",
      "|    total_timesteps      | 40960    |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.71e+20 |\n",
      "|    n_updates            | 190      |\n",
      "|    policy_gradient_loss | 1.04e-08 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.52e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.59e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 21        |\n",
      "|    time_elapsed         | 139       |\n",
      "|    total_timesteps      | 43008     |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.89e+20  |\n",
      "|    n_updates            | 200       |\n",
      "|    policy_gradient_loss | -1.36e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.76e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.59e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 22        |\n",
      "|    time_elapsed         | 146       |\n",
      "|    total_timesteps      | 45056     |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.69e+20  |\n",
      "|    n_updates            | 210       |\n",
      "|    policy_gradient_loss | -4.9e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.35e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.59e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 23            |\n",
      "|    time_elapsed         | 153           |\n",
      "|    total_timesteps      | 47104         |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.12e+20      |\n",
      "|    n_updates            | 220           |\n",
      "|    policy_gradient_loss | 2.67e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 8e+20         |\n",
      "-------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.59e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 307      |\n",
      "|    iterations           | 24       |\n",
      "|    time_elapsed         | 159      |\n",
      "|    total_timesteps      | 49152    |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.49e+20 |\n",
      "|    n_updates            | 230      |\n",
      "|    policy_gradient_loss | 4.05e-10 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 6.71e+20 |\n",
      "--------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.59e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 307      |\n",
      "|    iterations           | 25       |\n",
      "|    time_elapsed         | 166      |\n",
      "|    total_timesteps      | 51200    |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.78e+20 |\n",
      "|    n_updates            | 240      |\n",
      "|    policy_gradient_loss | 8.82e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.44e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.59e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 26        |\n",
      "|    time_elapsed         | 173       |\n",
      "|    total_timesteps      | 53248     |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.82e+20  |\n",
      "|    n_updates            | 250       |\n",
      "|    policy_gradient_loss | -6.17e-10 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.43e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.59e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 27        |\n",
      "|    time_elapsed         | 179       |\n",
      "|    total_timesteps      | 55296     |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.37e+20  |\n",
      "|    n_updates            | 260       |\n",
      "|    policy_gradient_loss | -6.08e-10 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.17e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.59e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 28        |\n",
      "|    time_elapsed         | 186       |\n",
      "|    total_timesteps      | 57344     |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.01e+20  |\n",
      "|    n_updates            | 270       |\n",
      "|    policy_gradient_loss | -3.07e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 8.19e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.61e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 29            |\n",
      "|    time_elapsed         | 192           |\n",
      "|    total_timesteps      | 59392         |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 2.78e+20      |\n",
      "|    n_updates            | 280           |\n",
      "|    policy_gradient_loss | -1.64e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 6.88e+20      |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.6e+11       |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 30            |\n",
      "|    time_elapsed         | 199           |\n",
      "|    total_timesteps      | 61440         |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.14e+20      |\n",
      "|    n_updates            | 290           |\n",
      "|    policy_gradient_loss | 1.87e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 8.11e+20      |\n",
      "-------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.62e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 31       |\n",
      "|    time_elapsed         | 206      |\n",
      "|    total_timesteps      | 63488    |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.92e+20 |\n",
      "|    n_updates            | 300      |\n",
      "|    policy_gradient_loss | 2.99e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.51e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.64e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 32        |\n",
      "|    time_elapsed         | 212       |\n",
      "|    total_timesteps      | 65536     |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.27e+20  |\n",
      "|    n_updates            | 310       |\n",
      "|    policy_gradient_loss | 4.27e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.65e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.64e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 33       |\n",
      "|    time_elapsed         | 219      |\n",
      "|    total_timesteps      | 67584    |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 4.35e+20 |\n",
      "|    n_updates            | 320      |\n",
      "|    policy_gradient_loss | -7.1e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 8.61e+20 |\n",
      "--------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.63e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 34           |\n",
      "|    time_elapsed         | 225          |\n",
      "|    total_timesteps      | 69632        |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 5.820766e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.07e+20     |\n",
      "|    n_updates            | 330          |\n",
      "|    policy_gradient_loss | 4.04e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.28e+20     |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.63e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 35            |\n",
      "|    time_elapsed         | 232           |\n",
      "|    total_timesteps      | 71680         |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.25e+20      |\n",
      "|    n_updates            | 340           |\n",
      "|    policy_gradient_loss | -1.33e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 6.93e+20      |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.62e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 36           |\n",
      "|    time_elapsed         | 239          |\n",
      "|    total_timesteps      | 73728        |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.7e+20      |\n",
      "|    n_updates            | 350          |\n",
      "|    policy_gradient_loss | 5.44e-10     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.46e+20     |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.62e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 37            |\n",
      "|    time_elapsed         | 245           |\n",
      "|    total_timesteps      | 75776         |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 2.51e+20      |\n",
      "|    n_updates            | 360           |\n",
      "|    policy_gradient_loss | 7.37e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 6.79e+20      |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.63e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 38           |\n",
      "|    time_elapsed         | 252          |\n",
      "|    total_timesteps      | 77824        |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 4.31e+20     |\n",
      "|    n_updates            | 370          |\n",
      "|    policy_gradient_loss | 7.54e-10     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.89e+20     |\n",
      "------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.62e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 39           |\n",
      "|    time_elapsed         | 258          |\n",
      "|    total_timesteps      | 79872        |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.61e+20     |\n",
      "|    n_updates            | 380          |\n",
      "|    policy_gradient_loss | -1.65e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.02e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.63e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 40        |\n",
      "|    time_elapsed         | 265       |\n",
      "|    total_timesteps      | 81920     |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.13e+20  |\n",
      "|    n_updates            | 390       |\n",
      "|    policy_gradient_loss | -1.05e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.72e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.63e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 41            |\n",
      "|    time_elapsed         | 271           |\n",
      "|    total_timesteps      | 83968         |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.44e+20      |\n",
      "|    n_updates            | 400           |\n",
      "|    policy_gradient_loss | 9.9e-11       |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.51e+20      |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.65e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 42            |\n",
      "|    time_elapsed         | 278           |\n",
      "|    total_timesteps      | 86016         |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.82e+20      |\n",
      "|    n_updates            | 410           |\n",
      "|    policy_gradient_loss | 3.73e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.65e+20      |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.64e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 43            |\n",
      "|    time_elapsed         | 285           |\n",
      "|    total_timesteps      | 88064         |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.15e+20      |\n",
      "|    n_updates            | 420           |\n",
      "|    policy_gradient_loss | 1.07e-08      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 8.22e+20      |\n",
      "-------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.62e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 309      |\n",
      "|    iterations           | 44       |\n",
      "|    time_elapsed         | 291      |\n",
      "|    total_timesteps      | 90112    |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.26e+20 |\n",
      "|    n_updates            | 430      |\n",
      "|    policy_gradient_loss | -6.7e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 6.38e+20 |\n",
      "--------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.63e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 309           |\n",
      "|    iterations           | 45            |\n",
      "|    time_elapsed         | 298           |\n",
      "|    total_timesteps      | 92160         |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.17e+20      |\n",
      "|    n_updates            | 440           |\n",
      "|    policy_gradient_loss | -3.11e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.41e+20      |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.63e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 46           |\n",
      "|    time_elapsed         | 304          |\n",
      "|    total_timesteps      | 94208        |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.36e+20     |\n",
      "|    n_updates            | 450          |\n",
      "|    policy_gradient_loss | -1.6e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 6.61e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.64e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 47        |\n",
      "|    time_elapsed         | 311       |\n",
      "|    total_timesteps      | 96256     |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.51e+20  |\n",
      "|    n_updates            | 460       |\n",
      "|    policy_gradient_loss | -2.65e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.34e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.64e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 48            |\n",
      "|    time_elapsed         | 318           |\n",
      "|    total_timesteps      | 98304         |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.17e+20      |\n",
      "|    n_updates            | 470           |\n",
      "|    policy_gradient_loss | -2.4e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.91e+20      |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.63e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 49           |\n",
      "|    time_elapsed         | 325          |\n",
      "|    total_timesteps      | 100352       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.99e+20     |\n",
      "|    n_updates            | 480          |\n",
      "|    policy_gradient_loss | -1.58e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.04e+20     |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.65e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 50            |\n",
      "|    time_elapsed         | 331           |\n",
      "|    total_timesteps      | 102400        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.47e+20      |\n",
      "|    n_updates            | 490           |\n",
      "|    policy_gradient_loss | 1.78e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 8.01e+20      |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.65e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 51        |\n",
      "|    time_elapsed         | 338       |\n",
      "|    total_timesteps      | 104448    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.19e+20  |\n",
      "|    n_updates            | 500       |\n",
      "|    policy_gradient_loss | -4e-09    |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.91e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.67e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 52       |\n",
      "|    time_elapsed         | 345      |\n",
      "|    total_timesteps      | 106496   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 4.02e+20 |\n",
      "|    n_updates            | 510      |\n",
      "|    policy_gradient_loss | 7.63e-10 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.35e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.65e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 53        |\n",
      "|    time_elapsed         | 351       |\n",
      "|    total_timesteps      | 108544    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.7e+20   |\n",
      "|    n_updates            | 520       |\n",
      "|    policy_gradient_loss | -4.46e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.62e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.66e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 54            |\n",
      "|    time_elapsed         | 358           |\n",
      "|    total_timesteps      | 110592        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 1.7462298e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.5e+20       |\n",
      "|    n_updates            | 530           |\n",
      "|    policy_gradient_loss | 2.7e-09       |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 6.65e+20      |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.66e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 55            |\n",
      "|    time_elapsed         | 365           |\n",
      "|    total_timesteps      | 112640        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 2.3283064e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.57e+20      |\n",
      "|    n_updates            | 540           |\n",
      "|    policy_gradient_loss | -4.66e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 8.58e+20      |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.68e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 56            |\n",
      "|    time_elapsed         | 371           |\n",
      "|    total_timesteps      | 114688        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 1.7462298e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 2.89e+20      |\n",
      "|    n_updates            | 550           |\n",
      "|    policy_gradient_loss | -1.26e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.07e+20      |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.66e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 57           |\n",
      "|    time_elapsed         | 378          |\n",
      "|    total_timesteps      | 116736       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.73e+20     |\n",
      "|    n_updates            | 560          |\n",
      "|    policy_gradient_loss | 3.36e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.93e+20     |\n",
      "------------------------------------------\n",
      "--------------------------------------------\n",
      "| rollout/                |                |\n",
      "|    ep_len_mean          | 601            |\n",
      "|    ep_rew_mean          | 8.65e+11       |\n",
      "| time/                   |                |\n",
      "|    fps                  | 308            |\n",
      "|    iterations           | 58             |\n",
      "|    time_elapsed         | 385            |\n",
      "|    total_timesteps      | 118784         |\n",
      "| train/                  |                |\n",
      "|    approx_kl            | -2.0372681e-10 |\n",
      "|    clip_fraction        | 0              |\n",
      "|    clip_range           | 0.2            |\n",
      "|    entropy_loss         | -1.42          |\n",
      "|    explained_variance   | 0              |\n",
      "|    learning_rate        | 0.0003         |\n",
      "|    loss                 | 3.49e+20       |\n",
      "|    n_updates            | 570            |\n",
      "|    policy_gradient_loss | 3.67e-09       |\n",
      "|    std                  | 1              |\n",
      "|    value_loss           | 7.24e+20       |\n",
      "--------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.64e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 59        |\n",
      "|    time_elapsed         | 391       |\n",
      "|    total_timesteps      | 120832    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 2.87e+20  |\n",
      "|    n_updates            | 580       |\n",
      "|    policy_gradient_loss | -2.44e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.7e+20   |\n",
      "---------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.64e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 60       |\n",
      "|    time_elapsed         | 398      |\n",
      "|    total_timesteps      | 122880   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 4.35e+20 |\n",
      "|    n_updates            | 590      |\n",
      "|    policy_gradient_loss | 9.02e-10 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.98e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.63e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 61        |\n",
      "|    time_elapsed         | 404       |\n",
      "|    total_timesteps      | 124928    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.22e+20  |\n",
      "|    n_updates            | 600       |\n",
      "|    policy_gradient_loss | -1.74e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.01e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.62e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 62            |\n",
      "|    time_elapsed         | 411           |\n",
      "|    total_timesteps      | 126976        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 1.1641532e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.65e+20      |\n",
      "|    n_updates            | 610           |\n",
      "|    policy_gradient_loss | 4.34e-10      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.57e+20      |\n",
      "-------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.62e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 63       |\n",
      "|    time_elapsed         | 418      |\n",
      "|    total_timesteps      | 129024   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.07e+20 |\n",
      "|    n_updates            | 620      |\n",
      "|    policy_gradient_loss | 8.41e-10 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.21e+20 |\n",
      "--------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.64e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 64       |\n",
      "|    time_elapsed         | 424      |\n",
      "|    total_timesteps      | 131072   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.94e+20 |\n",
      "|    n_updates            | 630      |\n",
      "|    policy_gradient_loss | 4.04e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.44e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.65e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 65        |\n",
      "|    time_elapsed         | 431       |\n",
      "|    total_timesteps      | 133120    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.45e+20  |\n",
      "|    n_updates            | 640       |\n",
      "|    policy_gradient_loss | -4.02e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 8.26e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------------\n",
      "| rollout/                |                |\n",
      "|    ep_len_mean          | 601            |\n",
      "|    ep_rew_mean          | 8.65e+11       |\n",
      "| time/                   |                |\n",
      "|    fps                  | 308            |\n",
      "|    iterations           | 66             |\n",
      "|    time_elapsed         | 437            |\n",
      "|    total_timesteps      | 135168         |\n",
      "| train/                  |                |\n",
      "|    approx_kl            | -1.4551915e-10 |\n",
      "|    clip_fraction        | 0              |\n",
      "|    clip_range           | 0.2            |\n",
      "|    entropy_loss         | -1.42          |\n",
      "|    explained_variance   | -1.19e-07      |\n",
      "|    learning_rate        | 0.0003         |\n",
      "|    loss                 | 3.24e+20       |\n",
      "|    n_updates            | 650            |\n",
      "|    policy_gradient_loss | -7.53e-09      |\n",
      "|    std                  | 1              |\n",
      "|    value_loss           | 7.25e+20       |\n",
      "--------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.63e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 67            |\n",
      "|    time_elapsed         | 444           |\n",
      "|    total_timesteps      | 137216        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 2.6193447e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.49e+20      |\n",
      "|    n_updates            | 660           |\n",
      "|    policy_gradient_loss | -9.75e-10     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.22e+20      |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.63e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 68           |\n",
      "|    time_elapsed         | 451          |\n",
      "|    total_timesteps      | 139264       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 5.820766e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.36e+20     |\n",
      "|    n_updates            | 670          |\n",
      "|    policy_gradient_loss | 4.05e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 6.64e+20     |\n",
      "------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.62e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 69       |\n",
      "|    time_elapsed         | 457      |\n",
      "|    total_timesteps      | 141312   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 4.4e+20  |\n",
      "|    n_updates            | 680      |\n",
      "|    policy_gradient_loss | 2.14e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.54e+20 |\n",
      "--------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.62e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 70       |\n",
      "|    time_elapsed         | 464      |\n",
      "|    total_timesteps      | 143360   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.52e+20 |\n",
      "|    n_updates            | 690      |\n",
      "|    policy_gradient_loss | 4.44e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.43e+20 |\n",
      "--------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.61e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 71       |\n",
      "|    time_elapsed         | 471      |\n",
      "|    total_timesteps      | 145408   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.75e+20 |\n",
      "|    n_updates            | 700      |\n",
      "|    policy_gradient_loss | 1.57e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.35e+20 |\n",
      "--------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.62e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 72       |\n",
      "|    time_elapsed         | 478      |\n",
      "|    total_timesteps      | 147456   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.54e+20 |\n",
      "|    n_updates            | 710      |\n",
      "|    policy_gradient_loss | 3.18e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.9e+20  |\n",
      "--------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.63e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 73           |\n",
      "|    time_elapsed         | 485          |\n",
      "|    total_timesteps      | 149504       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.12e+20     |\n",
      "|    n_updates            | 720          |\n",
      "|    policy_gradient_loss | -3.43e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7e+20        |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.63e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 74            |\n",
      "|    time_elapsed         | 491           |\n",
      "|    total_timesteps      | 151552        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.43e+20      |\n",
      "|    n_updates            | 730           |\n",
      "|    policy_gradient_loss | 3.68e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.32e+20      |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.63e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 75            |\n",
      "|    time_elapsed         | 498           |\n",
      "|    total_timesteps      | 153600        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.3e+20       |\n",
      "|    n_updates            | 740           |\n",
      "|    policy_gradient_loss | 5.75e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.27e+20      |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.62e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 76        |\n",
      "|    time_elapsed         | 505       |\n",
      "|    total_timesteps      | 155648    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.25e+20  |\n",
      "|    n_updates            | 750       |\n",
      "|    policy_gradient_loss | -7.98e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.22e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.64e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 77        |\n",
      "|    time_elapsed         | 511       |\n",
      "|    total_timesteps      | 157696    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.46e+20  |\n",
      "|    n_updates            | 760       |\n",
      "|    policy_gradient_loss | -9.47e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 8.11e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.65e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 307      |\n",
      "|    iterations           | 78       |\n",
      "|    time_elapsed         | 518      |\n",
      "|    total_timesteps      | 159744   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 4.8e+20  |\n",
      "|    n_updates            | 770      |\n",
      "|    policy_gradient_loss | 7.7e-09  |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.45e+20 |\n",
      "--------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.64e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 307          |\n",
      "|    iterations           | 79           |\n",
      "|    time_elapsed         | 525          |\n",
      "|    total_timesteps      | 161792       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.52e+20     |\n",
      "|    n_updates            | 780          |\n",
      "|    policy_gradient_loss | -1.09e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 8.03e+20     |\n",
      "------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.64e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 307          |\n",
      "|    iterations           | 80           |\n",
      "|    time_elapsed         | 531          |\n",
      "|    total_timesteps      | 163840       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.44e+20     |\n",
      "|    n_updates            | 790          |\n",
      "|    policy_gradient_loss | -1.34e-10    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.34e+20     |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.64e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 81            |\n",
      "|    time_elapsed         | 538           |\n",
      "|    total_timesteps      | 165888        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.67e+20      |\n",
      "|    n_updates            | 800           |\n",
      "|    policy_gradient_loss | -4.87e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 6.82e+20      |\n",
      "-------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.64e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 307      |\n",
      "|    iterations           | 82       |\n",
      "|    time_elapsed         | 545      |\n",
      "|    total_timesteps      | 167936   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 4.25e+20 |\n",
      "|    n_updates            | 810      |\n",
      "|    policy_gradient_loss | 6.9e-09  |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 8.02e+20 |\n",
      "--------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.64e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 83            |\n",
      "|    time_elapsed         | 551           |\n",
      "|    total_timesteps      | 169984        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.73e+20      |\n",
      "|    n_updates            | 820           |\n",
      "|    policy_gradient_loss | 1.06e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 6.56e+20      |\n",
      "-------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.63e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 84       |\n",
      "|    time_elapsed         | 558      |\n",
      "|    total_timesteps      | 172032   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 4.39e+20 |\n",
      "|    n_updates            | 830      |\n",
      "|    policy_gradient_loss | 6.23e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.77e+20 |\n",
      "--------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.63e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 85            |\n",
      "|    time_elapsed         | 565           |\n",
      "|    total_timesteps      | 174080        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 2.0372681e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.28e+20      |\n",
      "|    n_updates            | 840           |\n",
      "|    policy_gradient_loss | 2.09e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.28e+20      |\n",
      "-------------------------------------------\n",
      "--------------------------------------------\n",
      "| rollout/                |                |\n",
      "|    ep_len_mean          | 601            |\n",
      "|    ep_rew_mean          | 8.63e+11       |\n",
      "| time/                   |                |\n",
      "|    fps                  | 307            |\n",
      "|    iterations           | 86             |\n",
      "|    time_elapsed         | 572            |\n",
      "|    total_timesteps      | 176128         |\n",
      "| train/                  |                |\n",
      "|    approx_kl            | -1.7462298e-10 |\n",
      "|    clip_fraction        | 0              |\n",
      "|    clip_range           | 0.2            |\n",
      "|    entropy_loss         | -1.42          |\n",
      "|    explained_variance   | 0              |\n",
      "|    learning_rate        | 0.0003         |\n",
      "|    loss                 | 3.39e+20       |\n",
      "|    n_updates            | 850            |\n",
      "|    policy_gradient_loss | 3.62e-09       |\n",
      "|    std                  | 1              |\n",
      "|    value_loss           | 7.58e+20       |\n",
      "--------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.66e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 87        |\n",
      "|    time_elapsed         | 578       |\n",
      "|    total_timesteps      | 178176    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -2.38e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.77e+20  |\n",
      "|    n_updates            | 860       |\n",
      "|    policy_gradient_loss | -6e-09    |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.84e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.66e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 88        |\n",
      "|    time_elapsed         | 585       |\n",
      "|    total_timesteps      | 180224    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.77e+20  |\n",
      "|    n_updates            | 870       |\n",
      "|    policy_gradient_loss | -1.66e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.08e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.66e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 89        |\n",
      "|    time_elapsed         | 592       |\n",
      "|    total_timesteps      | 182272    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.75e+20  |\n",
      "|    n_updates            | 880       |\n",
      "|    policy_gradient_loss | -5.66e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.9e+20   |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.66e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 307          |\n",
      "|    iterations           | 90           |\n",
      "|    time_elapsed         | 598          |\n",
      "|    total_timesteps      | 184320       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.41e+20     |\n",
      "|    n_updates            | 890          |\n",
      "|    policy_gradient_loss | 1.07e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.39e+20     |\n",
      "------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.67e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 307      |\n",
      "|    iterations           | 91       |\n",
      "|    time_elapsed         | 605      |\n",
      "|    total_timesteps      | 186368   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.59e+20 |\n",
      "|    n_updates            | 900      |\n",
      "|    policy_gradient_loss | -5.2e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.35e+20 |\n",
      "--------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.66e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 307          |\n",
      "|    iterations           | 92           |\n",
      "|    time_elapsed         | 612          |\n",
      "|    total_timesteps      | 188416       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 8.731149e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.91e+20     |\n",
      "|    n_updates            | 910          |\n",
      "|    policy_gradient_loss | -1.26e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 8.09e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.65e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 93        |\n",
      "|    time_elapsed         | 619       |\n",
      "|    total_timesteps      | 190464    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 2.86e+20  |\n",
      "|    n_updates            | 920       |\n",
      "|    policy_gradient_loss | -1.74e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.42e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.65e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 94            |\n",
      "|    time_elapsed         | 626           |\n",
      "|    total_timesteps      | 192512        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.13e+20      |\n",
      "|    n_updates            | 930           |\n",
      "|    policy_gradient_loss | 7.95e-10      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 8.04e+20      |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.65e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 95            |\n",
      "|    time_elapsed         | 633           |\n",
      "|    total_timesteps      | 194560        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 1.4551915e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.92e+20      |\n",
      "|    n_updates            | 940           |\n",
      "|    policy_gradient_loss | 1.34e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.42e+20      |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.67e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 96        |\n",
      "|    time_elapsed         | 639       |\n",
      "|    total_timesteps      | 196608    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.69e+20  |\n",
      "|    n_updates            | 950       |\n",
      "|    policy_gradient_loss | 1.96e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.04e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.67e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 307      |\n",
      "|    iterations           | 97       |\n",
      "|    time_elapsed         | 646      |\n",
      "|    total_timesteps      | 198656   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 4.81e+20 |\n",
      "|    n_updates            | 960      |\n",
      "|    policy_gradient_loss | 5.85e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 8.1e+20  |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.67e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 98        |\n",
      "|    time_elapsed         | 653       |\n",
      "|    total_timesteps      | 200704    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.93e+20  |\n",
      "|    n_updates            | 970       |\n",
      "|    policy_gradient_loss | 4.95e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.2e+20   |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.68e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 99        |\n",
      "|    time_elapsed         | 660       |\n",
      "|    total_timesteps      | 202752    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.75e+20  |\n",
      "|    n_updates            | 980       |\n",
      "|    policy_gradient_loss | -3.31e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 8.1e+20   |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.69e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 100           |\n",
      "|    time_elapsed         | 666           |\n",
      "|    total_timesteps      | 204800        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.16e+20      |\n",
      "|    n_updates            | 990           |\n",
      "|    policy_gradient_loss | -4.21e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.06e+20      |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.69e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 101           |\n",
      "|    time_elapsed         | 673           |\n",
      "|    total_timesteps      | 206848        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -8.731149e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.1e+20       |\n",
      "|    n_updates            | 1000          |\n",
      "|    policy_gradient_loss | 3.49e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.6e+20       |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.7e+11   |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 102       |\n",
      "|    time_elapsed         | 679       |\n",
      "|    total_timesteps      | 208896    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.46e+20  |\n",
      "|    n_updates            | 1010      |\n",
      "|    policy_gradient_loss | -4.23e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 8.04e+20  |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.7e+11      |\n",
      "| time/                   |              |\n",
      "|    fps                  | 307          |\n",
      "|    iterations           | 103          |\n",
      "|    time_elapsed         | 686          |\n",
      "|    total_timesteps      | 210944       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.53e+20     |\n",
      "|    n_updates            | 1020         |\n",
      "|    policy_gradient_loss | -2.27e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.27e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.69e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 104       |\n",
      "|    time_elapsed         | 693       |\n",
      "|    total_timesteps      | 212992    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.15e+20  |\n",
      "|    n_updates            | 1030      |\n",
      "|    policy_gradient_loss | -6.14e-10 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 8.04e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------------\n",
      "| rollout/                |                |\n",
      "|    ep_len_mean          | 601            |\n",
      "|    ep_rew_mean          | 8.7e+11        |\n",
      "| time/                   |                |\n",
      "|    fps                  | 307            |\n",
      "|    iterations           | 105            |\n",
      "|    time_elapsed         | 699            |\n",
      "|    total_timesteps      | 215040         |\n",
      "| train/                  |                |\n",
      "|    approx_kl            | -1.4551915e-10 |\n",
      "|    clip_fraction        | 0              |\n",
      "|    clip_range           | 0.2            |\n",
      "|    entropy_loss         | -1.42          |\n",
      "|    explained_variance   | -1.19e-07      |\n",
      "|    learning_rate        | 0.0003         |\n",
      "|    loss                 | 2.98e+20       |\n",
      "|    n_updates            | 1040           |\n",
      "|    policy_gradient_loss | 4.92e-09       |\n",
      "|    std                  | 1              |\n",
      "|    value_loss           | 6.48e+20       |\n",
      "--------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.69e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 307      |\n",
      "|    iterations           | 106      |\n",
      "|    time_elapsed         | 706      |\n",
      "|    total_timesteps      | 217088   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 4.4e+20  |\n",
      "|    n_updates            | 1050     |\n",
      "|    policy_gradient_loss | 2.12e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.6e+20  |\n",
      "--------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.68e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 307      |\n",
      "|    iterations           | 107      |\n",
      "|    time_elapsed         | 713      |\n",
      "|    total_timesteps      | 219136   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.93e+20 |\n",
      "|    n_updates            | 1060     |\n",
      "|    policy_gradient_loss | 1.12e-08 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.37e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.68e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 108       |\n",
      "|    time_elapsed         | 719       |\n",
      "|    total_timesteps      | 221184    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.51e+20  |\n",
      "|    n_updates            | 1070      |\n",
      "|    policy_gradient_loss | -7.58e-10 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.43e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.69e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 109           |\n",
      "|    time_elapsed         | 726           |\n",
      "|    total_timesteps      | 223232        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.42e+20      |\n",
      "|    n_updates            | 1080          |\n",
      "|    policy_gradient_loss | -1.91e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 8.34e+20      |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.69e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 110       |\n",
      "|    time_elapsed         | 733       |\n",
      "|    total_timesteps      | 225280    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.01e+20  |\n",
      "|    n_updates            | 1090      |\n",
      "|    policy_gradient_loss | -3.17e-10 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.45e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.69e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 111       |\n",
      "|    time_elapsed         | 739       |\n",
      "|    total_timesteps      | 227328    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.57e+20  |\n",
      "|    n_updates            | 1100      |\n",
      "|    policy_gradient_loss | -1.47e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.72e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.69e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 307      |\n",
      "|    iterations           | 112      |\n",
      "|    time_elapsed         | 746      |\n",
      "|    total_timesteps      | 229376   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.44e+20 |\n",
      "|    n_updates            | 1110     |\n",
      "|    policy_gradient_loss | -7.1e-10 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.55e+20 |\n",
      "--------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.69e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 307      |\n",
      "|    iterations           | 113      |\n",
      "|    time_elapsed         | 753      |\n",
      "|    total_timesteps      | 231424   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 2.91e+20 |\n",
      "|    n_updates            | 1120     |\n",
      "|    policy_gradient_loss | 1.29e-08 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.22e+20 |\n",
      "--------------------------------------\n",
      "--------------------------------------------\n",
      "| rollout/                |                |\n",
      "|    ep_len_mean          | 601            |\n",
      "|    ep_rew_mean          | 8.68e+11       |\n",
      "| time/                   |                |\n",
      "|    fps                  | 307            |\n",
      "|    iterations           | 114            |\n",
      "|    time_elapsed         | 760            |\n",
      "|    total_timesteps      | 233472         |\n",
      "| train/                  |                |\n",
      "|    approx_kl            | -1.1641532e-10 |\n",
      "|    clip_fraction        | 0              |\n",
      "|    clip_range           | 0.2            |\n",
      "|    entropy_loss         | -1.42          |\n",
      "|    explained_variance   | 0              |\n",
      "|    learning_rate        | 0.0003         |\n",
      "|    loss                 | 4.18e+20       |\n",
      "|    n_updates            | 1130           |\n",
      "|    policy_gradient_loss | -3.49e-09      |\n",
      "|    std                  | 1              |\n",
      "|    value_loss           | 7.99e+20       |\n",
      "--------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.69e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 307          |\n",
      "|    iterations           | 115          |\n",
      "|    time_elapsed         | 766          |\n",
      "|    total_timesteps      | 235520       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.49e+20     |\n",
      "|    n_updates            | 1140         |\n",
      "|    policy_gradient_loss | -5.62e-10    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 6.98e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.68e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 116       |\n",
      "|    time_elapsed         | 773       |\n",
      "|    total_timesteps      | 237568    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -2.38e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.13e+20  |\n",
      "|    n_updates            | 1150      |\n",
      "|    policy_gradient_loss | 2.58e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.67e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.67e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 117           |\n",
      "|    time_elapsed         | 779           |\n",
      "|    total_timesteps      | 239616        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 2.3283064e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.24e+20      |\n",
      "|    n_updates            | 1160          |\n",
      "|    policy_gradient_loss | -4.64e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.08e+20      |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.67e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 118       |\n",
      "|    time_elapsed         | 786       |\n",
      "|    total_timesteps      | 241664    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.8e+20   |\n",
      "|    n_updates            | 1170      |\n",
      "|    policy_gradient_loss | -1.2e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.3e+20   |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.65e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 119           |\n",
      "|    time_elapsed         | 792           |\n",
      "|    total_timesteps      | 243712        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 1.1641532e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.04e+20      |\n",
      "|    n_updates            | 1180          |\n",
      "|    policy_gradient_loss | -3.09e-10     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.8e+20       |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.66e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 120           |\n",
      "|    time_elapsed         | 799           |\n",
      "|    total_timesteps      | 245760        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.45e+20      |\n",
      "|    n_updates            | 1190          |\n",
      "|    policy_gradient_loss | 4.03e-10      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 6.61e+20      |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.66e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 121           |\n",
      "|    time_elapsed         | 805           |\n",
      "|    total_timesteps      | 247808        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.63e+20      |\n",
      "|    n_updates            | 1200          |\n",
      "|    policy_gradient_loss | -5.43e-10     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 8.45e+20      |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.66e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 307          |\n",
      "|    iterations           | 122          |\n",
      "|    time_elapsed         | 811          |\n",
      "|    total_timesteps      | 249856       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 5.820766e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.99e+20     |\n",
      "|    n_updates            | 1210         |\n",
      "|    policy_gradient_loss | 1.86e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 6.59e+20     |\n",
      "------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.65e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 307          |\n",
      "|    iterations           | 123          |\n",
      "|    time_elapsed         | 818          |\n",
      "|    total_timesteps      | 251904       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.85e+20     |\n",
      "|    n_updates            | 1220         |\n",
      "|    policy_gradient_loss | -1.14e-08    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.44e+20     |\n",
      "------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.65e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 124      |\n",
      "|    time_elapsed         | 824      |\n",
      "|    total_timesteps      | 253952   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.3e+20  |\n",
      "|    n_updates            | 1230     |\n",
      "|    policy_gradient_loss | 2.21e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.75e+20 |\n",
      "--------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.65e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 125          |\n",
      "|    time_elapsed         | 830          |\n",
      "|    total_timesteps      | 256000       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.37e+20     |\n",
      "|    n_updates            | 1240         |\n",
      "|    policy_gradient_loss | -4.63e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 6.79e+20     |\n",
      "------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.64e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 126          |\n",
      "|    time_elapsed         | 836          |\n",
      "|    total_timesteps      | 258048       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.11e+20     |\n",
      "|    n_updates            | 1250         |\n",
      "|    policy_gradient_loss | -5.74e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.72e+20     |\n",
      "------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.63e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 127      |\n",
      "|    time_elapsed         | 843      |\n",
      "|    total_timesteps      | 260096   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.79e+20 |\n",
      "|    n_updates            | 1260     |\n",
      "|    policy_gradient_loss | 3.38e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 6.82e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.64e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 128       |\n",
      "|    time_elapsed         | 849       |\n",
      "|    total_timesteps      | 262144    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.91e+20  |\n",
      "|    n_updates            | 1270      |\n",
      "|    policy_gradient_loss | 3.41e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.62e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.64e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 129      |\n",
      "|    time_elapsed         | 856      |\n",
      "|    total_timesteps      | 264192   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 4.33e+20 |\n",
      "|    n_updates            | 1280     |\n",
      "|    policy_gradient_loss | 4.79e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 8.22e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.64e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 130       |\n",
      "|    time_elapsed         | 862       |\n",
      "|    total_timesteps      | 266240    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.22e+20  |\n",
      "|    n_updates            | 1290      |\n",
      "|    policy_gradient_loss | -1.57e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.75e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.62e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 131           |\n",
      "|    time_elapsed         | 868           |\n",
      "|    total_timesteps      | 268288        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 1.4551915e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.14e+20      |\n",
      "|    n_updates            | 1300          |\n",
      "|    policy_gradient_loss | -3.55e-10     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 8.36e+20      |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.62e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 132           |\n",
      "|    time_elapsed         | 875           |\n",
      "|    total_timesteps      | 270336        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.27e+20      |\n",
      "|    n_updates            | 1310          |\n",
      "|    policy_gradient_loss | 6.04e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 6.36e+20      |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.62e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 133          |\n",
      "|    time_elapsed         | 881          |\n",
      "|    total_timesteps      | 272384       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 4.09e+20     |\n",
      "|    n_updates            | 1320         |\n",
      "|    policy_gradient_loss | -5.18e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.34e+20     |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.61e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 309           |\n",
      "|    iterations           | 134           |\n",
      "|    time_elapsed         | 887           |\n",
      "|    total_timesteps      | 274432        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.58e+20      |\n",
      "|    n_updates            | 1330          |\n",
      "|    policy_gradient_loss | -1.22e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.27e+20      |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.61e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 309       |\n",
      "|    iterations           | 135       |\n",
      "|    time_elapsed         | 894       |\n",
      "|    total_timesteps      | 276480    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.35e+20  |\n",
      "|    n_updates            | 1340      |\n",
      "|    policy_gradient_loss | -2.39e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.82e+20  |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.61e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 309          |\n",
      "|    iterations           | 136          |\n",
      "|    time_elapsed         | 900          |\n",
      "|    total_timesteps      | 278528       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 4.12e+20     |\n",
      "|    n_updates            | 1350         |\n",
      "|    policy_gradient_loss | -2.61e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 8.26e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.59e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 309       |\n",
      "|    iterations           | 137       |\n",
      "|    time_elapsed         | 907       |\n",
      "|    total_timesteps      | 280576    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.59e+20  |\n",
      "|    n_updates            | 1360      |\n",
      "|    policy_gradient_loss | -4.31e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.52e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.59e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 309       |\n",
      "|    iterations           | 138       |\n",
      "|    time_elapsed         | 913       |\n",
      "|    total_timesteps      | 282624    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.44e+20  |\n",
      "|    n_updates            | 1370      |\n",
      "|    policy_gradient_loss | 1.35e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.26e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.58e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 309      |\n",
      "|    iterations           | 139      |\n",
      "|    time_elapsed         | 919      |\n",
      "|    total_timesteps      | 284672   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.68e+20 |\n",
      "|    n_updates            | 1380     |\n",
      "|    policy_gradient_loss | 4.9e-09  |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.15e+20 |\n",
      "--------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.59e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 309           |\n",
      "|    iterations           | 140           |\n",
      "|    time_elapsed         | 926           |\n",
      "|    total_timesteps      | 286720        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.53e+20      |\n",
      "|    n_updates            | 1390          |\n",
      "|    policy_gradient_loss | -3.98e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 6.89e+20      |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.59e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 309          |\n",
      "|    iterations           | 141          |\n",
      "|    time_elapsed         | 932          |\n",
      "|    total_timesteps      | 288768       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 5.04e+20     |\n",
      "|    n_updates            | 1400         |\n",
      "|    policy_gradient_loss | 3.41e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 8.59e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.57e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 309       |\n",
      "|    iterations           | 142       |\n",
      "|    time_elapsed         | 938       |\n",
      "|    total_timesteps      | 290816    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.64e+20  |\n",
      "|    n_updates            | 1410      |\n",
      "|    policy_gradient_loss | -2.99e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.82e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.57e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 309       |\n",
      "|    iterations           | 143       |\n",
      "|    time_elapsed         | 944       |\n",
      "|    total_timesteps      | 292864    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.05e+20  |\n",
      "|    n_updates            | 1420      |\n",
      "|    policy_gradient_loss | -1.03e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.54e+20  |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.58e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 310          |\n",
      "|    iterations           | 144          |\n",
      "|    time_elapsed         | 951          |\n",
      "|    total_timesteps      | 294912       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 8.731149e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.29e+20     |\n",
      "|    n_updates            | 1430         |\n",
      "|    policy_gradient_loss | -5.52e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 6.57e+20     |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.57e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 310           |\n",
      "|    iterations           | 145           |\n",
      "|    time_elapsed         | 957           |\n",
      "|    total_timesteps      | 296960        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.79e+20      |\n",
      "|    n_updates            | 1440          |\n",
      "|    policy_gradient_loss | 9.34e-10      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.39e+20      |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.58e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 310          |\n",
      "|    iterations           | 146          |\n",
      "|    time_elapsed         | 963          |\n",
      "|    total_timesteps      | 299008       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.6e+20      |\n",
      "|    n_updates            | 1450         |\n",
      "|    policy_gradient_loss | -1.21e-08    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.85e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.57e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 310       |\n",
      "|    iterations           | 147       |\n",
      "|    time_elapsed         | 970       |\n",
      "|    total_timesteps      | 301056    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.8e+20   |\n",
      "|    n_updates            | 1460      |\n",
      "|    policy_gradient_loss | -2.56e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.97e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.59e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 310       |\n",
      "|    iterations           | 148       |\n",
      "|    time_elapsed         | 976       |\n",
      "|    total_timesteps      | 303104    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.77e+20  |\n",
      "|    n_updates            | 1470      |\n",
      "|    policy_gradient_loss | -5.72e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 8.11e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.6e+11       |\n",
      "| time/                   |               |\n",
      "|    fps                  | 310           |\n",
      "|    iterations           | 149           |\n",
      "|    time_elapsed         | 983           |\n",
      "|    total_timesteps      | 305152        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -8.731149e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.35e+20      |\n",
      "|    n_updates            | 1480          |\n",
      "|    policy_gradient_loss | -3.17e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.27e+20      |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.61e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 310           |\n",
      "|    iterations           | 150           |\n",
      "|    time_elapsed         | 989           |\n",
      "|    total_timesteps      | 307200        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -8.731149e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.86e+20      |\n",
      "|    n_updates            | 1490          |\n",
      "|    policy_gradient_loss | -1.05e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.64e+20      |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.61e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 310          |\n",
      "|    iterations           | 151          |\n",
      "|    time_elapsed         | 995          |\n",
      "|    total_timesteps      | 309248       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 5.820766e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 4.36e+20     |\n",
      "|    n_updates            | 1500         |\n",
      "|    policy_gradient_loss | -5.21e-10    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 8.21e+20     |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.6e+11       |\n",
      "| time/                   |               |\n",
      "|    fps                  | 310           |\n",
      "|    iterations           | 152           |\n",
      "|    time_elapsed         | 1002          |\n",
      "|    total_timesteps      | 311296        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 1.7462298e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4e+20         |\n",
      "|    n_updates            | 1510          |\n",
      "|    policy_gradient_loss | 2.01e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 6.84e+20      |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.6e+11      |\n",
      "| time/                   |              |\n",
      "|    fps                  | 310          |\n",
      "|    iterations           | 153          |\n",
      "|    time_elapsed         | 1008         |\n",
      "|    total_timesteps      | 313344       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.96e+20     |\n",
      "|    n_updates            | 1520         |\n",
      "|    policy_gradient_loss | 1.63e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.87e+20     |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.59e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 310           |\n",
      "|    iterations           | 154           |\n",
      "|    time_elapsed         | 1014          |\n",
      "|    total_timesteps      | 315392        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 2.64e+20      |\n",
      "|    n_updates            | 1530          |\n",
      "|    policy_gradient_loss | -3.11e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 6.15e+20      |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.59e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 310           |\n",
      "|    iterations           | 155           |\n",
      "|    time_elapsed         | 1020          |\n",
      "|    total_timesteps      | 317440        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 1.1641532e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.85e+20      |\n",
      "|    n_updates            | 1540          |\n",
      "|    policy_gradient_loss | -8.58e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.28e+20      |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.6e+11       |\n",
      "| time/                   |               |\n",
      "|    fps                  | 311           |\n",
      "|    iterations           | 156           |\n",
      "|    time_elapsed         | 1027          |\n",
      "|    total_timesteps      | 319488        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.16e+20      |\n",
      "|    n_updates            | 1550          |\n",
      "|    policy_gradient_loss | -2.01e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.75e+20      |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.58e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 311       |\n",
      "|    iterations           | 157       |\n",
      "|    time_elapsed         | 1033      |\n",
      "|    total_timesteps      | 321536    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.25e+20  |\n",
      "|    n_updates            | 1560      |\n",
      "|    policy_gradient_loss | -1.96e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.13e+20  |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.58e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 311          |\n",
      "|    iterations           | 158          |\n",
      "|    time_elapsed         | 1040         |\n",
      "|    total_timesteps      | 323584       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -2.38e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.72e+20     |\n",
      "|    n_updates            | 1570         |\n",
      "|    policy_gradient_loss | -2.49e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.97e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.58e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 311       |\n",
      "|    iterations           | 159       |\n",
      "|    time_elapsed         | 1046      |\n",
      "|    total_timesteps      | 325632    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.67e+20  |\n",
      "|    n_updates            | 1580      |\n",
      "|    policy_gradient_loss | -1.06e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.72e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.58e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 311           |\n",
      "|    iterations           | 160           |\n",
      "|    time_elapsed         | 1052          |\n",
      "|    total_timesteps      | 327680        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.86e+20      |\n",
      "|    n_updates            | 1590          |\n",
      "|    policy_gradient_loss | -3.42e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.59e+20      |\n",
      "-------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.59e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 311      |\n",
      "|    iterations           | 161      |\n",
      "|    time_elapsed         | 1058     |\n",
      "|    total_timesteps      | 329728   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.92e+20 |\n",
      "|    n_updates            | 1600     |\n",
      "|    policy_gradient_loss | 4.93e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.36e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.59e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 311       |\n",
      "|    iterations           | 162       |\n",
      "|    time_elapsed         | 1065      |\n",
      "|    total_timesteps      | 331776    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.62e+20  |\n",
      "|    n_updates            | 1610      |\n",
      "|    policy_gradient_loss | -2.09e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.25e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.6e+11       |\n",
      "| time/                   |               |\n",
      "|    fps                  | 311           |\n",
      "|    iterations           | 163           |\n",
      "|    time_elapsed         | 1072          |\n",
      "|    total_timesteps      | 333824        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 1.1641532e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.58e+20      |\n",
      "|    n_updates            | 1620          |\n",
      "|    policy_gradient_loss | -5.06e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 8.1e+20       |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.61e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 311           |\n",
      "|    iterations           | 164           |\n",
      "|    time_elapsed         | 1078          |\n",
      "|    total_timesteps      | 335872        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -8.731149e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.62e+20      |\n",
      "|    n_updates            | 1630          |\n",
      "|    policy_gradient_loss | 4.85e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 6.93e+20      |\n",
      "-------------------------------------------\n",
      "--------------------------------------------\n",
      "| rollout/                |                |\n",
      "|    ep_len_mean          | 601            |\n",
      "|    ep_rew_mean          | 8.61e+11       |\n",
      "| time/                   |                |\n",
      "|    fps                  | 311            |\n",
      "|    iterations           | 165            |\n",
      "|    time_elapsed         | 1084           |\n",
      "|    total_timesteps      | 337920         |\n",
      "| train/                  |                |\n",
      "|    approx_kl            | -1.7462298e-10 |\n",
      "|    clip_fraction        | 0              |\n",
      "|    clip_range           | 0.2            |\n",
      "|    entropy_loss         | -1.42          |\n",
      "|    explained_variance   | -1.19e-07      |\n",
      "|    learning_rate        | 0.0003         |\n",
      "|    loss                 | 3.69e+20       |\n",
      "|    n_updates            | 1640           |\n",
      "|    policy_gradient_loss | -3.42e-09      |\n",
      "|    std                  | 1              |\n",
      "|    value_loss           | 8.06e+20       |\n",
      "--------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.62e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 311       |\n",
      "|    iterations           | 166       |\n",
      "|    time_elapsed         | 1091      |\n",
      "|    total_timesteps      | 339968    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.86e+20  |\n",
      "|    n_updates            | 1650      |\n",
      "|    policy_gradient_loss | -1.39e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.25e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.62e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 311       |\n",
      "|    iterations           | 167       |\n",
      "|    time_elapsed         | 1097      |\n",
      "|    total_timesteps      | 342016    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.36e+20  |\n",
      "|    n_updates            | 1660      |\n",
      "|    policy_gradient_loss | 2.51e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.95e+20  |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.63e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 311          |\n",
      "|    iterations           | 168          |\n",
      "|    time_elapsed         | 1103         |\n",
      "|    total_timesteps      | 344064       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.84e+20     |\n",
      "|    n_updates            | 1670         |\n",
      "|    policy_gradient_loss | 1.31e-10     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.74e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.64e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 311       |\n",
      "|    iterations           | 169       |\n",
      "|    time_elapsed         | 1110      |\n",
      "|    total_timesteps      | 346112    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.85e+20  |\n",
      "|    n_updates            | 1680      |\n",
      "|    policy_gradient_loss | 2.5e-09   |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.09e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.63e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 311       |\n",
      "|    iterations           | 170       |\n",
      "|    time_elapsed         | 1116      |\n",
      "|    total_timesteps      | 348160    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.58e+20  |\n",
      "|    n_updates            | 1690      |\n",
      "|    policy_gradient_loss | -1.57e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 8.12e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.65e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 311       |\n",
      "|    iterations           | 171       |\n",
      "|    time_elapsed         | 1123      |\n",
      "|    total_timesteps      | 350208    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 2.88e+20  |\n",
      "|    n_updates            | 1700      |\n",
      "|    policy_gradient_loss | -2.62e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.43e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.65e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 311       |\n",
      "|    iterations           | 172       |\n",
      "|    time_elapsed         | 1129      |\n",
      "|    total_timesteps      | 352256    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.39e+20  |\n",
      "|    n_updates            | 1710      |\n",
      "|    policy_gradient_loss | -5.16e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.11e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.65e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 311      |\n",
      "|    iterations           | 173      |\n",
      "|    time_elapsed         | 1136     |\n",
      "|    total_timesteps      | 354304   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.92e+20 |\n",
      "|    n_updates            | 1720     |\n",
      "|    policy_gradient_loss | 1.08e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.98e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.63e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 311       |\n",
      "|    iterations           | 174       |\n",
      "|    time_elapsed         | 1143      |\n",
      "|    total_timesteps      | 356352    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.47e+20  |\n",
      "|    n_updates            | 1730      |\n",
      "|    policy_gradient_loss | 3.02e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.93e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.65e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 311      |\n",
      "|    iterations           | 175      |\n",
      "|    time_elapsed         | 1149     |\n",
      "|    total_timesteps      | 358400   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.88e+20 |\n",
      "|    n_updates            | 1740     |\n",
      "|    policy_gradient_loss | 4.55e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.44e+20 |\n",
      "--------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.65e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 311          |\n",
      "|    iterations           | 176          |\n",
      "|    time_elapsed         | 1156         |\n",
      "|    total_timesteps      | 360448       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.04e+20     |\n",
      "|    n_updates            | 1750         |\n",
      "|    policy_gradient_loss | -1.49e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.06e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.65e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 311       |\n",
      "|    iterations           | 177       |\n",
      "|    time_elapsed         | 1163      |\n",
      "|    total_timesteps      | 362496    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.63e+20  |\n",
      "|    n_updates            | 1760      |\n",
      "|    policy_gradient_loss | 7.19e-10  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.68e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------------\n",
      "| rollout/                |                |\n",
      "|    ep_len_mean          | 601            |\n",
      "|    ep_rew_mean          | 8.64e+11       |\n",
      "| time/                   |                |\n",
      "|    fps                  | 311            |\n",
      "|    iterations           | 178            |\n",
      "|    time_elapsed         | 1170           |\n",
      "|    total_timesteps      | 364544         |\n",
      "| train/                  |                |\n",
      "|    approx_kl            | -1.4551915e-10 |\n",
      "|    clip_fraction        | 0              |\n",
      "|    clip_range           | 0.2            |\n",
      "|    entropy_loss         | -1.42          |\n",
      "|    explained_variance   | 0              |\n",
      "|    learning_rate        | 0.0003         |\n",
      "|    loss                 | 3.73e+20       |\n",
      "|    n_updates            | 1770           |\n",
      "|    policy_gradient_loss | -4.8e-10       |\n",
      "|    std                  | 1              |\n",
      "|    value_loss           | 8.09e+20       |\n",
      "--------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.63e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 311       |\n",
      "|    iterations           | 179       |\n",
      "|    time_elapsed         | 1176      |\n",
      "|    total_timesteps      | 366592    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.99e+20  |\n",
      "|    n_updates            | 1780      |\n",
      "|    policy_gradient_loss | -5.09e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.05e+20  |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.62e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 311          |\n",
      "|    iterations           | 180          |\n",
      "|    time_elapsed         | 1183         |\n",
      "|    total_timesteps      | 368640       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.6e+20      |\n",
      "|    n_updates            | 1790         |\n",
      "|    policy_gradient_loss | -4.17e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.91e+20     |\n",
      "------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.63e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 311          |\n",
      "|    iterations           | 181          |\n",
      "|    time_elapsed         | 1190         |\n",
      "|    total_timesteps      | 370688       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 5.820766e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.23e+20     |\n",
      "|    n_updates            | 1800         |\n",
      "|    policy_gradient_loss | 3.55e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 6.3e+20      |\n",
      "------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.63e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 311      |\n",
      "|    iterations           | 182      |\n",
      "|    time_elapsed         | 1197     |\n",
      "|    total_timesteps      | 372736   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.88e+20 |\n",
      "|    n_updates            | 1810     |\n",
      "|    policy_gradient_loss | 3.87e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.55e+20 |\n",
      "--------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.64e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 311           |\n",
      "|    iterations           | 183           |\n",
      "|    time_elapsed         | 1203          |\n",
      "|    total_timesteps      | 374784        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.95e+20      |\n",
      "|    n_updates            | 1820          |\n",
      "|    policy_gradient_loss | -5.22e-10     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.24e+20      |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.64e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 311       |\n",
      "|    iterations           | 184       |\n",
      "|    time_elapsed         | 1210      |\n",
      "|    total_timesteps      | 376832    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.49e+20  |\n",
      "|    n_updates            | 1830      |\n",
      "|    policy_gradient_loss | 3.16e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.13e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.64e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 311       |\n",
      "|    iterations           | 185       |\n",
      "|    time_elapsed         | 1217      |\n",
      "|    total_timesteps      | 378880    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.05e+20  |\n",
      "|    n_updates            | 1840      |\n",
      "|    policy_gradient_loss | 8.54e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 8.17e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.64e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 311      |\n",
      "|    iterations           | 186      |\n",
      "|    time_elapsed         | 1223     |\n",
      "|    total_timesteps      | 380928   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 2.91e+20 |\n",
      "|    n_updates            | 1850     |\n",
      "|    policy_gradient_loss | 4.47e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 6.75e+20 |\n",
      "--------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.66e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 311      |\n",
      "|    iterations           | 187      |\n",
      "|    time_elapsed         | 1230     |\n",
      "|    total_timesteps      | 382976   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.65e+20 |\n",
      "|    n_updates            | 1860     |\n",
      "|    policy_gradient_loss | 1.96e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.6e+20  |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.64e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 311       |\n",
      "|    iterations           | 188       |\n",
      "|    time_elapsed         | 1237      |\n",
      "|    total_timesteps      | 385024    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.39e+20  |\n",
      "|    n_updates            | 1870      |\n",
      "|    policy_gradient_loss | -4.21e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.77e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.65e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 310           |\n",
      "|    iterations           | 189           |\n",
      "|    time_elapsed         | 1244          |\n",
      "|    total_timesteps      | 387072        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 1.1641532e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.16e+20      |\n",
      "|    n_updates            | 1880          |\n",
      "|    policy_gradient_loss | -2.6e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 6.65e+20      |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.65e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 310       |\n",
      "|    iterations           | 190       |\n",
      "|    time_elapsed         | 1251      |\n",
      "|    total_timesteps      | 389120    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.93e+20  |\n",
      "|    n_updates            | 1890      |\n",
      "|    policy_gradient_loss | 1.39e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 8.18e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.65e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 310       |\n",
      "|    iterations           | 191       |\n",
      "|    time_elapsed         | 1258      |\n",
      "|    total_timesteps      | 391168    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.31e+20  |\n",
      "|    n_updates            | 1900      |\n",
      "|    policy_gradient_loss | -1.09e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.92e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.64e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 310       |\n",
      "|    iterations           | 192       |\n",
      "|    time_elapsed         | 1265      |\n",
      "|    total_timesteps      | 393216    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.42e+20  |\n",
      "|    n_updates            | 1910      |\n",
      "|    policy_gradient_loss | 3.49e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.98e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.63e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 310           |\n",
      "|    iterations           | 193           |\n",
      "|    time_elapsed         | 1273          |\n",
      "|    total_timesteps      | 395264        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -8.731149e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.98e+20      |\n",
      "|    n_updates            | 1920          |\n",
      "|    policy_gradient_loss | -9.79e-10     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 6.83e+20      |\n",
      "-------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.63e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 310      |\n",
      "|    iterations           | 194      |\n",
      "|    time_elapsed         | 1280     |\n",
      "|    total_timesteps      | 397312   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.5e+20  |\n",
      "|    n_updates            | 1930     |\n",
      "|    policy_gradient_loss | 1.64e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.09e+20 |\n",
      "--------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.62e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 310           |\n",
      "|    iterations           | 195           |\n",
      "|    time_elapsed         | 1286          |\n",
      "|    total_timesteps      | 399360        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -8.731149e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.15e+20      |\n",
      "|    n_updates            | 1940          |\n",
      "|    policy_gradient_loss | 1.91e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.95e+20      |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.62e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 310       |\n",
      "|    iterations           | 196       |\n",
      "|    time_elapsed         | 1293      |\n",
      "|    total_timesteps      | 401408    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.39e+20  |\n",
      "|    n_updates            | 1950      |\n",
      "|    policy_gradient_loss | -3.75e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.44e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.61e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 310      |\n",
      "|    iterations           | 197      |\n",
      "|    time_elapsed         | 1300     |\n",
      "|    total_timesteps      | 403456   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.92e+20 |\n",
      "|    n_updates            | 1960     |\n",
      "|    policy_gradient_loss | 2.71e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.42e+20 |\n",
      "--------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.62e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 310          |\n",
      "|    iterations           | 198          |\n",
      "|    time_elapsed         | 1307         |\n",
      "|    total_timesteps      | 405504       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -2.38e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 4.41e+20     |\n",
      "|    n_updates            | 1970         |\n",
      "|    policy_gradient_loss | 2.62e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 6.96e+20     |\n",
      "------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.62e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 310      |\n",
      "|    iterations           | 199      |\n",
      "|    time_elapsed         | 1314     |\n",
      "|    total_timesteps      | 407552   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 4.46e+20 |\n",
      "|    n_updates            | 1980     |\n",
      "|    policy_gradient_loss | 6.41e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.64e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.62e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 310       |\n",
      "|    iterations           | 200       |\n",
      "|    time_elapsed         | 1321      |\n",
      "|    total_timesteps      | 409600    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.18e+20  |\n",
      "|    n_updates            | 1990      |\n",
      "|    policy_gradient_loss | -2.67e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 8.2e+20   |\n",
      "---------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.6e+11  |\n",
      "| time/                   |          |\n",
      "|    fps                  | 309      |\n",
      "|    iterations           | 201      |\n",
      "|    time_elapsed         | 1328     |\n",
      "|    total_timesteps      | 411648   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 4.13e+20 |\n",
      "|    n_updates            | 2000     |\n",
      "|    policy_gradient_loss | 7.92e-10 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.34e+20 |\n",
      "--------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.61e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 309          |\n",
      "|    iterations           | 202          |\n",
      "|    time_elapsed         | 1335         |\n",
      "|    total_timesteps      | 413696       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.53e+20     |\n",
      "|    n_updates            | 2010         |\n",
      "|    policy_gradient_loss | -3.51e-10    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.15e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.61e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 309       |\n",
      "|    iterations           | 203       |\n",
      "|    time_elapsed         | 1341      |\n",
      "|    total_timesteps      | 415744    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.48e+20  |\n",
      "|    n_updates            | 2020      |\n",
      "|    policy_gradient_loss | 1.69e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.11e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.61e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 309       |\n",
      "|    iterations           | 204       |\n",
      "|    time_elapsed         | 1348      |\n",
      "|    total_timesteps      | 417792    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.07e+20  |\n",
      "|    n_updates            | 2030      |\n",
      "|    policy_gradient_loss | -4.74e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.08e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.6e+11       |\n",
      "| time/                   |               |\n",
      "|    fps                  | 309           |\n",
      "|    iterations           | 205           |\n",
      "|    time_elapsed         | 1355          |\n",
      "|    total_timesteps      | 419840        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 1.1641532e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.17e+20      |\n",
      "|    n_updates            | 2040          |\n",
      "|    policy_gradient_loss | -3.94e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.87e+20      |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.59e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 309       |\n",
      "|    iterations           | 206       |\n",
      "|    time_elapsed         | 1362      |\n",
      "|    total_timesteps      | 421888    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.76e+20  |\n",
      "|    n_updates            | 2050      |\n",
      "|    policy_gradient_loss | 3.55e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.46e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.57e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 309       |\n",
      "|    iterations           | 207       |\n",
      "|    time_elapsed         | 1369      |\n",
      "|    total_timesteps      | 423936    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.56e+20  |\n",
      "|    n_updates            | 2060      |\n",
      "|    policy_gradient_loss | -1.75e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 8.04e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.57e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 309       |\n",
      "|    iterations           | 208       |\n",
      "|    time_elapsed         | 1376      |\n",
      "|    total_timesteps      | 425984    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 2.79e+20  |\n",
      "|    n_updates            | 2070      |\n",
      "|    policy_gradient_loss | -1.17e-08 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.1e+20   |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.58e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 309           |\n",
      "|    iterations           | 209           |\n",
      "|    time_elapsed         | 1383          |\n",
      "|    total_timesteps      | 428032        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 2.6193447e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.41e+20      |\n",
      "|    n_updates            | 2080          |\n",
      "|    policy_gradient_loss | 9.74e-10      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.75e+20      |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.58e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 309           |\n",
      "|    iterations           | 210           |\n",
      "|    time_elapsed         | 1390          |\n",
      "|    total_timesteps      | 430080        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 1.7462298e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.14e+20      |\n",
      "|    n_updates            | 2090          |\n",
      "|    policy_gradient_loss | -5.02e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.2e+20       |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.58e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 309           |\n",
      "|    iterations           | 211           |\n",
      "|    time_elapsed         | 1397          |\n",
      "|    total_timesteps      | 432128        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | 1.7462298e-10 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.71e+20      |\n",
      "|    n_updates            | 2100          |\n",
      "|    policy_gradient_loss | 3.52e-10      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.23e+20      |\n",
      "-------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.58e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 309      |\n",
      "|    iterations           | 212      |\n",
      "|    time_elapsed         | 1403     |\n",
      "|    total_timesteps      | 434176   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 4.44e+20 |\n",
      "|    n_updates            | 2110     |\n",
      "|    policy_gradient_loss | 2.95e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 7.7e+20  |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.57e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 309       |\n",
      "|    iterations           | 213       |\n",
      "|    time_elapsed         | 1410      |\n",
      "|    total_timesteps      | 436224    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.98e+20  |\n",
      "|    n_updates            | 2120      |\n",
      "|    policy_gradient_loss | -4.42e-10 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.62e+20  |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.58e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 309          |\n",
      "|    iterations           | 214          |\n",
      "|    time_elapsed         | 1417         |\n",
      "|    total_timesteps      | 438272       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.47e+20     |\n",
      "|    n_updates            | 2130         |\n",
      "|    policy_gradient_loss | -1.04e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.43e+20     |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.59e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 309           |\n",
      "|    iterations           | 215           |\n",
      "|    time_elapsed         | 1424          |\n",
      "|    total_timesteps      | 440320        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.59e+20      |\n",
      "|    n_updates            | 2140          |\n",
      "|    policy_gradient_loss | -6.51e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.91e+20      |\n",
      "-------------------------------------------\n",
      "--------------------------------------------\n",
      "| rollout/                |                |\n",
      "|    ep_len_mean          | 601            |\n",
      "|    ep_rew_mean          | 8.58e+11       |\n",
      "| time/                   |                |\n",
      "|    fps                  | 308            |\n",
      "|    iterations           | 216            |\n",
      "|    time_elapsed         | 1431           |\n",
      "|    total_timesteps      | 442368         |\n",
      "| train/                  |                |\n",
      "|    approx_kl            | -1.1641532e-10 |\n",
      "|    clip_fraction        | 0              |\n",
      "|    clip_range           | 0.2            |\n",
      "|    entropy_loss         | -1.42          |\n",
      "|    explained_variance   | 0              |\n",
      "|    learning_rate        | 0.0003         |\n",
      "|    loss                 | 3.57e+20       |\n",
      "|    n_updates            | 2150           |\n",
      "|    policy_gradient_loss | -2.45e-09      |\n",
      "|    std                  | 1              |\n",
      "|    value_loss           | 7.32e+20       |\n",
      "--------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.58e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 217           |\n",
      "|    time_elapsed         | 1438          |\n",
      "|    total_timesteps      | 444416        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -8.731149e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.72e+20      |\n",
      "|    n_updates            | 2160          |\n",
      "|    policy_gradient_loss | 8.11e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.65e+20      |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.56e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 218          |\n",
      "|    time_elapsed         | 1445         |\n",
      "|    total_timesteps      | 446464       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 5.820766e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.21e+20     |\n",
      "|    n_updates            | 2170         |\n",
      "|    policy_gradient_loss | -4.02e-10    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 6.93e+20     |\n",
      "------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.55e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 219      |\n",
      "|    time_elapsed         | 1452     |\n",
      "|    total_timesteps      | 448512   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 5.96e-08 |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.26e+20 |\n",
      "|    n_updates            | 2180     |\n",
      "|    policy_gradient_loss | 2.76e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 6.84e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.55e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 220       |\n",
      "|    time_elapsed         | 1460      |\n",
      "|    total_timesteps      | 450560    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.45e+20  |\n",
      "|    n_updates            | 2190      |\n",
      "|    policy_gradient_loss | 4.91e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.09e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.56e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 221       |\n",
      "|    time_elapsed         | 1467      |\n",
      "|    total_timesteps      | 452608    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.4e+20   |\n",
      "|    n_updates            | 2200      |\n",
      "|    policy_gradient_loss | 2.73e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.29e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.57e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 222      |\n",
      "|    time_elapsed         | 1474     |\n",
      "|    total_timesteps      | 454656   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.69e+20 |\n",
      "|    n_updates            | 2210     |\n",
      "|    policy_gradient_loss | 3.09e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 8.16e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.56e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 223       |\n",
      "|    time_elapsed         | 1481      |\n",
      "|    total_timesteps      | 456704    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.4e+20   |\n",
      "|    n_updates            | 2220      |\n",
      "|    policy_gradient_loss | -2.49e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.83e+20  |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.58e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 224          |\n",
      "|    time_elapsed         | 1487         |\n",
      "|    total_timesteps      | 458752       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 4.23e+20     |\n",
      "|    n_updates            | 2230         |\n",
      "|    policy_gradient_loss | 6.27e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.98e+20     |\n",
      "------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.57e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 225      |\n",
      "|    time_elapsed         | 1494     |\n",
      "|    total_timesteps      | 460800   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.31e+20 |\n",
      "|    n_updates            | 2240     |\n",
      "|    policy_gradient_loss | 1.68e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 6.97e+20 |\n",
      "--------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.57e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 226          |\n",
      "|    time_elapsed         | 1501         |\n",
      "|    total_timesteps      | 462848       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 5.820766e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.34e+20     |\n",
      "|    n_updates            | 2250         |\n",
      "|    policy_gradient_loss | 1.34e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.23e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.56e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 227       |\n",
      "|    time_elapsed         | 1508      |\n",
      "|    total_timesteps      | 464896    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.18e+20  |\n",
      "|    n_updates            | 2260      |\n",
      "|    policy_gradient_loss | -1.05e-08 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.11e+20  |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.55e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 228          |\n",
      "|    time_elapsed         | 1514         |\n",
      "|    total_timesteps      | 466944       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.67e+20     |\n",
      "|    n_updates            | 2270         |\n",
      "|    policy_gradient_loss | 9.96e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 6.88e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.53e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 229       |\n",
      "|    time_elapsed         | 1521      |\n",
      "|    total_timesteps      | 468992    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.16e+20  |\n",
      "|    n_updates            | 2280      |\n",
      "|    policy_gradient_loss | -1.16e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.4e+20   |\n",
      "---------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.54e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 308      |\n",
      "|    iterations           | 230      |\n",
      "|    time_elapsed         | 1528     |\n",
      "|    total_timesteps      | 471040   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.63e+20 |\n",
      "|    n_updates            | 2290     |\n",
      "|    policy_gradient_loss | 1.45e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 6.63e+20 |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.53e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 231       |\n",
      "|    time_elapsed         | 1534      |\n",
      "|    total_timesteps      | 473088    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.48e+20  |\n",
      "|    n_updates            | 2300      |\n",
      "|    policy_gradient_loss | -3.34e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.29e+20  |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.53e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 232          |\n",
      "|    time_elapsed         | 1541         |\n",
      "|    total_timesteps      | 475136       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 8.731149e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.87e+20     |\n",
      "|    n_updates            | 2310         |\n",
      "|    policy_gradient_loss | -4.51e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.1e+20      |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.53e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 233           |\n",
      "|    time_elapsed         | 1548          |\n",
      "|    total_timesteps      | 477184        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.61e+20      |\n",
      "|    n_updates            | 2320          |\n",
      "|    policy_gradient_loss | 2.87e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 6.51e+20      |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.52e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 234       |\n",
      "|    time_elapsed         | 1554      |\n",
      "|    total_timesteps      | 479232    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.23e+20  |\n",
      "|    n_updates            | 2330      |\n",
      "|    policy_gradient_loss | -5.88e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 8.24e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.52e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 235       |\n",
      "|    time_elapsed         | 1562      |\n",
      "|    total_timesteps      | 481280    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.22e+20  |\n",
      "|    n_updates            | 2340      |\n",
      "|    policy_gradient_loss | -2.38e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.19e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.51e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 236           |\n",
      "|    time_elapsed         | 1568          |\n",
      "|    total_timesteps      | 483328        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.3e+20       |\n",
      "|    n_updates            | 2350          |\n",
      "|    policy_gradient_loss | -1.01e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.09e+20      |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.51e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 237          |\n",
      "|    time_elapsed         | 1575         |\n",
      "|    total_timesteps      | 485376       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 2.9e+20      |\n",
      "|    n_updates            | 2360         |\n",
      "|    policy_gradient_loss | -2.64e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 6.85e+20     |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.52e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 238           |\n",
      "|    time_elapsed         | 1582          |\n",
      "|    total_timesteps      | 487424        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.95e+20      |\n",
      "|    n_updates            | 2370          |\n",
      "|    policy_gradient_loss | -3.15e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.31e+20      |\n",
      "-------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.52e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 239           |\n",
      "|    time_elapsed         | 1588          |\n",
      "|    total_timesteps      | 489472        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -8.731149e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.58e+20      |\n",
      "|    n_updates            | 2380          |\n",
      "|    policy_gradient_loss | 5.26e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 8.31e+20      |\n",
      "-------------------------------------------\n",
      "--------------------------------------------\n",
      "| rollout/                |                |\n",
      "|    ep_len_mean          | 601            |\n",
      "|    ep_rew_mean          | 8.53e+11       |\n",
      "| time/                   |                |\n",
      "|    fps                  | 308            |\n",
      "|    iterations           | 240            |\n",
      "|    time_elapsed         | 1595           |\n",
      "|    total_timesteps      | 491520         |\n",
      "| train/                  |                |\n",
      "|    approx_kl            | -2.6193447e-10 |\n",
      "|    clip_fraction        | 0              |\n",
      "|    clip_range           | 0.2            |\n",
      "|    entropy_loss         | -1.42          |\n",
      "|    explained_variance   | 0              |\n",
      "|    learning_rate        | 0.0003         |\n",
      "|    loss                 | 3.16e+20       |\n",
      "|    n_updates            | 2390           |\n",
      "|    policy_gradient_loss | -2.83e-09      |\n",
      "|    std                  | 1              |\n",
      "|    value_loss           | 6.82e+20       |\n",
      "--------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.53e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 241          |\n",
      "|    time_elapsed         | 1602         |\n",
      "|    total_timesteps      | 493568       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.39e+20     |\n",
      "|    n_updates            | 2400         |\n",
      "|    policy_gradient_loss | 2.51e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.5e+20      |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.53e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 242           |\n",
      "|    time_elapsed         | 1608          |\n",
      "|    total_timesteps      | 495616        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -8.731149e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.06e+20      |\n",
      "|    n_updates            | 2410          |\n",
      "|    policy_gradient_loss | -6.89e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.06e+20      |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.51e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 243       |\n",
      "|    time_elapsed         | 1615      |\n",
      "|    total_timesteps      | 497664    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.18e+20  |\n",
      "|    n_updates            | 2420      |\n",
      "|    policy_gradient_loss | -3.41e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.76e+20  |\n",
      "---------------------------------------\n",
      "--------------------------------------------\n",
      "| rollout/                |                |\n",
      "|    ep_len_mean          | 601            |\n",
      "|    ep_rew_mean          | 8.49e+11       |\n",
      "| time/                   |                |\n",
      "|    fps                  | 308            |\n",
      "|    iterations           | 244            |\n",
      "|    time_elapsed         | 1622           |\n",
      "|    total_timesteps      | 499712         |\n",
      "| train/                  |                |\n",
      "|    approx_kl            | -1.1641532e-10 |\n",
      "|    clip_fraction        | 0              |\n",
      "|    clip_range           | 0.2            |\n",
      "|    entropy_loss         | -1.42          |\n",
      "|    explained_variance   | -1.19e-07      |\n",
      "|    learning_rate        | 0.0003         |\n",
      "|    loss                 | 3.97e+20       |\n",
      "|    n_updates            | 2430           |\n",
      "|    policy_gradient_loss | -7.16e-09      |\n",
      "|    std                  | 1              |\n",
      "|    value_loss           | 7.5e+20        |\n",
      "--------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.51e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 245           |\n",
      "|    time_elapsed         | 1628          |\n",
      "|    total_timesteps      | 501760        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.48e+20      |\n",
      "|    n_updates            | 2440          |\n",
      "|    policy_gradient_loss | -2.81e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 6.7e+20       |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.51e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 246          |\n",
      "|    time_elapsed         | 1635         |\n",
      "|    total_timesteps      | 503808       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 8.731149e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 4.45e+20     |\n",
      "|    n_updates            | 2450         |\n",
      "|    policy_gradient_loss | 4.88e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.99e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.52e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 247       |\n",
      "|    time_elapsed         | 1641      |\n",
      "|    total_timesteps      | 505856    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4e+20     |\n",
      "|    n_updates            | 2460      |\n",
      "|    policy_gradient_loss | -3.23e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.21e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.53e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 248       |\n",
      "|    time_elapsed         | 1649      |\n",
      "|    total_timesteps      | 507904    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.82e+20  |\n",
      "|    n_updates            | 2470      |\n",
      "|    policy_gradient_loss | -6.64e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.33e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.52e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 249       |\n",
      "|    time_elapsed         | 1655      |\n",
      "|    total_timesteps      | 509952    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.87e+20  |\n",
      "|    n_updates            | 2480      |\n",
      "|    policy_gradient_loss | -2e-09    |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.59e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.52e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 250       |\n",
      "|    time_elapsed         | 1662      |\n",
      "|    total_timesteps      | 512000    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.21e+20  |\n",
      "|    n_updates            | 2490      |\n",
      "|    policy_gradient_loss | 1.76e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.45e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.51e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 251           |\n",
      "|    time_elapsed         | 1669          |\n",
      "|    total_timesteps      | 514048        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -2.910383e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.16e+20      |\n",
      "|    n_updates            | 2500          |\n",
      "|    policy_gradient_loss | 1.24e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.98e+20      |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.52e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 307          |\n",
      "|    iterations           | 252          |\n",
      "|    time_elapsed         | 1675         |\n",
      "|    total_timesteps      | 516096       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.71e+20     |\n",
      "|    n_updates            | 2510         |\n",
      "|    policy_gradient_loss | -3.89e-10    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 6.88e+20     |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.52e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 253           |\n",
      "|    time_elapsed         | 1682          |\n",
      "|    total_timesteps      | 518144        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.46e+20      |\n",
      "|    n_updates            | 2520          |\n",
      "|    policy_gradient_loss | 6.97e-10      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.13e+20      |\n",
      "-------------------------------------------\n",
      "--------------------------------------\n",
      "| rollout/                |          |\n",
      "|    ep_len_mean          | 601      |\n",
      "|    ep_rew_mean          | 8.52e+11 |\n",
      "| time/                   |          |\n",
      "|    fps                  | 307      |\n",
      "|    iterations           | 254      |\n",
      "|    time_elapsed         | 1689     |\n",
      "|    total_timesteps      | 520192   |\n",
      "| train/                  |          |\n",
      "|    approx_kl            | 0.0      |\n",
      "|    clip_fraction        | 0        |\n",
      "|    clip_range           | 0.2      |\n",
      "|    entropy_loss         | -1.42    |\n",
      "|    explained_variance   | 0        |\n",
      "|    learning_rate        | 0.0003   |\n",
      "|    loss                 | 3.25e+20 |\n",
      "|    n_updates            | 2530     |\n",
      "|    policy_gradient_loss | -3.5e-09 |\n",
      "|    std                  | 1        |\n",
      "|    value_loss           | 8.1e+20  |\n",
      "--------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.51e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 255       |\n",
      "|    time_elapsed         | 1695      |\n",
      "|    total_timesteps      | 522240    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.07e+20  |\n",
      "|    n_updates            | 2540      |\n",
      "|    policy_gradient_loss | -3.22e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.55e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.52e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 256       |\n",
      "|    time_elapsed         | 1702      |\n",
      "|    total_timesteps      | 524288    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.85e+20  |\n",
      "|    n_updates            | 2550      |\n",
      "|    policy_gradient_loss | 5.49e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.33e+20  |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.53e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 307          |\n",
      "|    iterations           | 257          |\n",
      "|    time_elapsed         | 1708         |\n",
      "|    total_timesteps      | 526336       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -2.38e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3e+20        |\n",
      "|    n_updates            | 2560         |\n",
      "|    policy_gradient_loss | 3.43e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.02e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.52e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 258       |\n",
      "|    time_elapsed         | 1715      |\n",
      "|    total_timesteps      | 528384    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.28e+20  |\n",
      "|    n_updates            | 2570      |\n",
      "|    policy_gradient_loss | -1.44e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.71e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.53e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 259       |\n",
      "|    time_elapsed         | 1722      |\n",
      "|    total_timesteps      | 530432    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.34e+20  |\n",
      "|    n_updates            | 2580      |\n",
      "|    policy_gradient_loss | -4.22e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.16e+20  |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.53e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 260          |\n",
      "|    time_elapsed         | 1728         |\n",
      "|    total_timesteps      | 532480       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 4.15e+20     |\n",
      "|    n_updates            | 2590         |\n",
      "|    policy_gradient_loss | 6.02e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.2e+20      |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.55e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 261           |\n",
      "|    time_elapsed         | 1735          |\n",
      "|    total_timesteps      | 534528        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -8.731149e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | 0             |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 5e+20         |\n",
      "|    n_updates            | 2600          |\n",
      "|    policy_gradient_loss | 4.48e-09      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 8.02e+20      |\n",
      "-------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.55e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 262          |\n",
      "|    time_elapsed         | 1741         |\n",
      "|    total_timesteps      | 536576       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 5.820766e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 4.15e+20     |\n",
      "|    n_updates            | 2610         |\n",
      "|    policy_gradient_loss | -5.84e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.04e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.55e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 263       |\n",
      "|    time_elapsed         | 1748      |\n",
      "|    total_timesteps      | 538624    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.89e+20  |\n",
      "|    n_updates            | 2620      |\n",
      "|    policy_gradient_loss | -3.63e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.62e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.57e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 264       |\n",
      "|    time_elapsed         | 1754      |\n",
      "|    total_timesteps      | 540672    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.73e+20  |\n",
      "|    n_updates            | 2630      |\n",
      "|    policy_gradient_loss | -2.57e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.07e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.58e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 265       |\n",
      "|    time_elapsed         | 1761      |\n",
      "|    total_timesteps      | 542720    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.3e+20   |\n",
      "|    n_updates            | 2640      |\n",
      "|    policy_gradient_loss | -5.97e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.42e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.59e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 266       |\n",
      "|    time_elapsed         | 1768      |\n",
      "|    total_timesteps      | 544768    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.58e+20  |\n",
      "|    n_updates            | 2650      |\n",
      "|    policy_gradient_loss | -1.79e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 8.32e+20  |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.58e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 267          |\n",
      "|    time_elapsed         | 1774         |\n",
      "|    total_timesteps      | 546816       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.5e+20      |\n",
      "|    n_updates            | 2660         |\n",
      "|    policy_gradient_loss | 6.34e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 6.9e+20      |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.58e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 268       |\n",
      "|    time_elapsed         | 1781      |\n",
      "|    total_timesteps      | 548864    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -2.38e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.39e+20  |\n",
      "|    n_updates            | 2670      |\n",
      "|    policy_gradient_loss | 2.16e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.59e+20  |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.58e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 269          |\n",
      "|    time_elapsed         | 1788         |\n",
      "|    total_timesteps      | 550912       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 4.3e+20      |\n",
      "|    n_updates            | 2680         |\n",
      "|    policy_gradient_loss | 6.27e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.17e+20     |\n",
      "------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.57e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 270          |\n",
      "|    time_elapsed         | 1795         |\n",
      "|    total_timesteps      | 552960       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 5.820766e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -1.19e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 4.02e+20     |\n",
      "|    n_updates            | 2690         |\n",
      "|    policy_gradient_loss | -1.96e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.08e+20     |\n",
      "------------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.58e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 308           |\n",
      "|    iterations           | 271           |\n",
      "|    time_elapsed         | 1801          |\n",
      "|    total_timesteps      | 555008        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 3.98e+20      |\n",
      "|    n_updates            | 2700          |\n",
      "|    policy_gradient_loss | 4.61e-10      |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.76e+20      |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.59e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 272       |\n",
      "|    time_elapsed         | 1808      |\n",
      "|    total_timesteps      | 557056    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | 0         |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 2.9e+20   |\n",
      "|    n_updates            | 2710      |\n",
      "|    policy_gradient_loss | -6.43e-10 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 6.67e+20  |\n",
      "---------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.59e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 273          |\n",
      "|    time_elapsed         | 1815         |\n",
      "|    total_timesteps      | 559104       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 2.910383e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | 0            |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 4.34e+20     |\n",
      "|    n_updates            | 2720         |\n",
      "|    policy_gradient_loss | 7.83e-09     |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.53e+20     |\n",
      "------------------------------------------\n",
      "------------------------------------------\n",
      "| rollout/                |              |\n",
      "|    ep_len_mean          | 601          |\n",
      "|    ep_rew_mean          | 8.58e+11     |\n",
      "| time/                   |              |\n",
      "|    fps                  | 308          |\n",
      "|    iterations           | 274          |\n",
      "|    time_elapsed         | 1821         |\n",
      "|    total_timesteps      | 561152       |\n",
      "| train/                  |              |\n",
      "|    approx_kl            | 5.820766e-11 |\n",
      "|    clip_fraction        | 0            |\n",
      "|    clip_range           | 0.2          |\n",
      "|    entropy_loss         | -1.42        |\n",
      "|    explained_variance   | -2.38e-07    |\n",
      "|    learning_rate        | 0.0003       |\n",
      "|    loss                 | 3.21e+20     |\n",
      "|    n_updates            | 2730         |\n",
      "|    policy_gradient_loss | -2.04e-09    |\n",
      "|    std                  | 1            |\n",
      "|    value_loss           | 7.01e+20     |\n",
      "------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.58e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 275       |\n",
      "|    time_elapsed         | 1828      |\n",
      "|    total_timesteps      | 563200    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -1.19e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.16e+20  |\n",
      "|    n_updates            | 2740      |\n",
      "|    policy_gradient_loss | -8.44e-09 |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.38e+20  |\n",
      "---------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.59e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 308       |\n",
      "|    iterations           | 276       |\n",
      "|    time_elapsed         | 1835      |\n",
      "|    total_timesteps      | 565248    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -2.38e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 4.1e+20   |\n",
      "|    n_updates            | 2750      |\n",
      "|    policy_gradient_loss | 2.26e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.69e+20  |\n",
      "---------------------------------------\n",
      "-------------------------------------------\n",
      "| rollout/                |               |\n",
      "|    ep_len_mean          | 601           |\n",
      "|    ep_rew_mean          | 8.59e+11      |\n",
      "| time/                   |               |\n",
      "|    fps                  | 307           |\n",
      "|    iterations           | 277           |\n",
      "|    time_elapsed         | 1841          |\n",
      "|    total_timesteps      | 567296        |\n",
      "| train/                  |               |\n",
      "|    approx_kl            | -5.820766e-11 |\n",
      "|    clip_fraction        | 0             |\n",
      "|    clip_range           | 0.2           |\n",
      "|    entropy_loss         | -1.42         |\n",
      "|    explained_variance   | -1.19e-07     |\n",
      "|    learning_rate        | 0.0003        |\n",
      "|    loss                 | 4.02e+20      |\n",
      "|    n_updates            | 2760          |\n",
      "|    policy_gradient_loss | -1.79e-09     |\n",
      "|    std                  | 1             |\n",
      "|    value_loss           | 7.44e+20      |\n",
      "-------------------------------------------\n",
      "---------------------------------------\n",
      "| rollout/                |           |\n",
      "|    ep_len_mean          | 601       |\n",
      "|    ep_rew_mean          | 8.59e+11  |\n",
      "| time/                   |           |\n",
      "|    fps                  | 307       |\n",
      "|    iterations           | 278       |\n",
      "|    time_elapsed         | 1848      |\n",
      "|    total_timesteps      | 569344    |\n",
      "| train/                  |           |\n",
      "|    approx_kl            | 0.0       |\n",
      "|    clip_fraction        | 0         |\n",
      "|    clip_range           | 0.2       |\n",
      "|    entropy_loss         | -1.42     |\n",
      "|    explained_variance   | -2.38e-07 |\n",
      "|    learning_rate        | 0.0003    |\n",
      "|    loss                 | 3.88e+20  |\n",
      "|    n_updates            | 2770      |\n",
      "|    policy_gradient_loss | 3.25e-09  |\n",
      "|    std                  | 1         |\n",
      "|    value_loss           | 7.91e+20  |\n",
      "---------------------------------------\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[25], line 4\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mstable_baselines3\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m PPO\n\u001b[1;32m      3\u001b[0m model \u001b[38;5;241m=\u001b[39m PPO(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMultiInputPolicy\u001b[39m\u001b[38;5;124m\"\u001b[39m, wrapped_env, verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m)\n\u001b[0;32m----> 4\u001b[0m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlearn\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtotal_timesteps\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m1_000_000\u001b[39;49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/Documents/Code/solarcarsim/.venv/lib/python3.12/site-packages/stable_baselines3/ppo/ppo.py:311\u001b[0m, in \u001b[0;36mPPO.learn\u001b[0;34m(self, total_timesteps, callback, log_interval, tb_log_name, reset_num_timesteps, progress_bar)\u001b[0m\n\u001b[1;32m    302\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mlearn\u001b[39m(\n\u001b[1;32m    303\u001b[0m     \u001b[38;5;28mself\u001b[39m: SelfPPO,\n\u001b[1;32m    304\u001b[0m     total_timesteps: \u001b[38;5;28mint\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    309\u001b[0m     progress_bar: \u001b[38;5;28mbool\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[1;32m    310\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m SelfPPO:\n\u001b[0;32m--> 311\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlearn\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    312\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtotal_timesteps\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtotal_timesteps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    313\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcallback\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallback\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    314\u001b[0m \u001b[43m        \u001b[49m\u001b[43mlog_interval\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlog_interval\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    315\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtb_log_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtb_log_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    316\u001b[0m \u001b[43m        \u001b[49m\u001b[43mreset_num_timesteps\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreset_num_timesteps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    317\u001b[0m \u001b[43m        \u001b[49m\u001b[43mprogress_bar\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprogress_bar\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    318\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/Documents/Code/solarcarsim/.venv/lib/python3.12/site-packages/stable_baselines3/common/on_policy_algorithm.py:336\u001b[0m, in \u001b[0;36mOnPolicyAlgorithm.learn\u001b[0;34m(self, total_timesteps, callback, log_interval, tb_log_name, reset_num_timesteps, progress_bar)\u001b[0m\n\u001b[1;32m    333\u001b[0m         \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mep_info_buffer \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    334\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_dump_logs(iteration)\n\u001b[0;32m--> 336\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrain\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    338\u001b[0m callback\u001b[38;5;241m.\u001b[39mon_training_end()\n\u001b[1;32m    340\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\n",
      "File \u001b[0;32m~/Documents/Code/solarcarsim/.venv/lib/python3.12/site-packages/stable_baselines3/ppo/ppo.py:213\u001b[0m, in \u001b[0;36mPPO.train\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    209\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maction_space, spaces\u001b[38;5;241m.\u001b[39mDiscrete):\n\u001b[1;32m    210\u001b[0m     \u001b[38;5;66;03m# Convert discrete action from float to long\u001b[39;00m\n\u001b[1;32m    211\u001b[0m     actions \u001b[38;5;241m=\u001b[39m rollout_data\u001b[38;5;241m.\u001b[39mactions\u001b[38;5;241m.\u001b[39mlong()\u001b[38;5;241m.\u001b[39mflatten()\n\u001b[0;32m--> 213\u001b[0m values, log_prob, entropy \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpolicy\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mevaluate_actions\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrollout_data\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mobservations\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mactions\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    214\u001b[0m values \u001b[38;5;241m=\u001b[39m values\u001b[38;5;241m.\u001b[39mflatten()\n\u001b[1;32m    215\u001b[0m \u001b[38;5;66;03m# Normalize advantage\u001b[39;00m\n",
      "File \u001b[0;32m~/Documents/Code/solarcarsim/.venv/lib/python3.12/site-packages/stable_baselines3/common/policies.py:739\u001b[0m, in \u001b[0;36mActorCriticPolicy.evaluate_actions\u001b[0;34m(self, obs, actions)\u001b[0m\n\u001b[1;32m    737\u001b[0m distribution \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_action_dist_from_latent(latent_pi)\n\u001b[1;32m    738\u001b[0m log_prob \u001b[38;5;241m=\u001b[39m distribution\u001b[38;5;241m.\u001b[39mlog_prob(actions)\n\u001b[0;32m--> 739\u001b[0m values \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mvalue_net\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlatent_vf\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    740\u001b[0m entropy \u001b[38;5;241m=\u001b[39m distribution\u001b[38;5;241m.\u001b[39mentropy()\n\u001b[1;32m    741\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m values, log_prob, entropy\n",
      "File \u001b[0;32m~/Documents/Code/solarcarsim/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py:1736\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1734\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1735\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1736\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/Documents/Code/solarcarsim/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py:1747\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1742\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1743\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1744\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1745\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1746\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1747\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1749\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1750\u001b[0m called_always_called_hooks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mset\u001b[39m()\n",
      "File \u001b[0;32m~/Documents/Code/solarcarsim/.venv/lib/python3.12/site-packages/torch/nn/modules/linear.py:125\u001b[0m, in \u001b[0;36mLinear.forward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m    124\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Tensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[0;32m--> 125\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mF\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlinear\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mweight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbias\u001b[49m\u001b[43m)\u001b[49m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "# import a model and try it out!\n",
    "from stable_baselines3 import PPO\n",
    "model = PPO(\"MultiInputPolicy\", wrapped_env, verbose=1)\n",
    "model.learn(total_timesteps=1_000_000)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Array([[[-4.9999666, -5.031969 , -5.063982 , ..., -6.714849 ,\n",
       "         -6.71299  , -6.7111654],\n",
       "        [-4.9998884, -5.031891 , -5.0639033, ..., -6.705859 ,\n",
       "         -6.7038655, -6.701909 ],\n",
       "        [-4.9997377, -5.03174  , -5.0637527, ..., -6.6968226,\n",
       "         -6.694696 , -6.692607 ],\n",
       "        ...,\n",
       "        [-4.8104963, -4.840162 , -4.869858 , ..., -6.505874 ,\n",
       "         -6.499703 , -6.4934487],\n",
       "        [-4.8117733, -4.8413825, -4.871023 , ..., -6.511339 ,\n",
       "         -6.5052385, -6.499054 ],\n",
       "        [-4.812991 , -4.8425455, -4.8721304, ..., -6.5165534,\n",
       "         -6.510523 , -6.504408 ]]], dtype=float32)"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pos = jnp.array([0])\n",
    "time = jnp.array([0])\n",
    "x = jnp.stack([pos,time], axis=1)\n",
    "vlookup(x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}