add dependencies to L3 solutions

Author: aamini

lab3/solutions/RL_Solution.ipynb

@@ -89,6 +89,10 @@
         "id": "EvdePP-VyVWp"
       },
       "source": [
+        "#Install some dependencies for visualizing the agents\n",
+        "!apt-get install -y xvfb python-opengl x11-utils > /dev/null 2>&1\n",
+        "!pip install gym pyvirtualdisplay scikit-video > /dev/null 2>&1\n",
+        "\n",
         "# Import Tensorflow 2.0\n",
         "%tensorflow_version 2.x\n",
         "import tensorflow as tf\n",
@@ -241,7 +245,7 @@
         "\n",
         "cartpole_model = create_cartpole_model()"
       ],
-      "execution_count": null,
+      "execution_count": 6,
       "outputs": []
     },
     {
@@ -289,7 +293,7 @@
         "\n",
         "  return action[0] if single else action"
       ],
-      "execution_count": null,
+      "execution_count": 7,
       "outputs": []
     },
     {
@@ -352,7 +356,7 @@
         "# Instantiate a single Memory buffer\n",
         "memory = Memory()"
       ],
-      "execution_count": null,
+      "execution_count": 8,
       "outputs": []
     },
     {
@@ -404,7 +408,7 @@
         "      \n",
         "  return normalize(discounted_rewards)"
       ],
-      "execution_count": null,
+      "execution_count": 9,
       "outputs": []
     },
     {
@@ -448,7 +452,7 @@
         "  # loss = tf.reduce_mean('''TODO''')\n",
         "  return loss"
       ],
-      "execution_count": null,
+      "execution_count": 10,
       "outputs": []
     },
     {
@@ -482,7 +486,7 @@
         "  # grads = tape.gradient('''TODO''', model.trainable_variables)\n",
         "  optimizer.apply_gradients(zip(grads, model.trainable_variables))\n"
       ],
-      "execution_count": null,
+      "execution_count": 11,
       "outputs": []
     },
     {