Remove a warning when computing left_proba

18_reinforcement_learning.ipynb

@@ -807,7 +807,7 @@
     "# extra code – a function that creates an animation for a given policy model\n",
     "\n",
     "def pg_policy(obs):\n",
-    "    left_proba = model.predict(obs[np.newaxis], verbose=0)\n",
+    "    left_proba = model.predict(obs[np.newaxis], verbose=0)[0][0]\n",
     "    return int(np.random.rand() > left_proba)\n",
     "\n",
     "np.random.seed(42)\n",

environment.yml

@@ -40,6 +40,6 @@ dependencies:
     - tensorflow~=2.14.0  # Deep Learning library
     - transformers~=4.35.0  # Natural Language Processing lib for TF or PyTorch
     - urlextract~=1.8.0  # optionally used in chapter 3, exercise 4
-    - gym[classic_control,atari,accept-rom-license]  # used only in ch18
+    - gymnasium[classic_control,atari,accept-rom-license]  # used only in ch18
     - google-cloud-aiplatform~=1.36.2  # used only in chapter 19
     - google-cloud-storage~=2.13.0  # used only in chapter 19