few fixes for hw2

Author: klensy

homeworks/hw02_cross_entropy/01_crossentropy_method.ipynb

@@ -622,9 +622,9 @@
         "\n",
         "In this section you will train a neural network policy for continuous state space game\n",
         "\n",
-        "You can find full description of the environment [here](https://www.gymlibrary.dev/environments/classic_control/cart_pole/).\n",
+        "You can find full description of the environment [here](https://gymnasium.farama.org/environments/classic_control/cart_pole/).\n",
         "\n",
-        "![CartPole-v0\"](https://www.gymlibrary.dev/_images/cart_pole.gif)\n",
+        "![CartPole-v0\"](https://gymnasium.farama.org/_images/cart_pole.gif)\n",
         "\n",
         "So here's how it works:"
       ]
@@ -684,7 +684,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Update the generate_session function and beat the game!"
+        "Update the generate_session_cartpole function and beat the game!"
       ]
     },
     {
@@ -772,7 +772,7 @@
         "sessions_to_send = []\n",
         "for session in sessions:\n",
         "  observations = [x.tolist() for x in session[0]]\n",
-        "  actions = [x.item() for x in session[1]]\n",
+        "  actions = [x.item() if hasattr(x, "item") else int(x) for x in session[1]]\n",
         "  sessions_to_send.append((observations, actions))\n",
         "\n",
         "import json\n",