updated to last version of OpenGym

ml5/2_6_1_Q-Learning.ipynb

@@ -97,16 +97,19 @@
    "source": [
     "import gym\n",
     "\n",
-    "env = gym.make('CartPole-v0')\n",
+    "env = gym.make(\"CartPole-v1\")\n",
     "#env = gym.make('MountainCar-v0')\n",
     "#env = gym.make('Taxi-v2')\n",
     "\n",
-    "#env = gym.make('Jamesbond-ram-v0')\n",
-    "\n",
-    "env.reset()\n",
+    "observation = env.reset()\n",
     "for _ in range(1000):\n",
-    "    env.render()\n",
-    "    env.step(env.action_space.sample()) # take a random action"
+    "  env.render()\n",
+    "  action = env.action_space.sample() # your agent here (this takes random actions)\n",
+    "  observation, reward, done, info = env.step(action)\n",
+    "\n",
+    "  if done:\n",
+    "    observation = env.reset()\n",
+    "env.close()"
    ]
   },
   {
@@ -403,6 +406,15 @@
   }
  ],
  "metadata": {
+  "datacleaner": {
+   "position": {
+    "top": "50px"
+   },
+   "python": {
+    "varRefreshCmd": "try:\n    print(_datacleaner.dataframe_metadata())\nexcept:\n    print([])"
+   },
+   "window_display": false
+  },
   "kernelspec": {
    "display_name": "Python 3",
    "language": "python",
@@ -418,7 +430,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.5"
+   "version": "3.7.9"
   },
   "latex_envs": {
    "LaTeX_envs_menu_present": true,