Created using Colab

Notebooks/Chap19/19_2_Dynamic_Programming.ipynb

@@ -4,7 +4,6 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyOlD6kmCxX3SKKuh3oJikKA",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -406,6 +405,10 @@
         "            state_values_new[state] = 3.0\n",
         "            break\n",
         "\n",
+        "        # TODO -- Write this function (from equation 19.11, but bear in mind policy is deterministic here)\n",
+        "        # Replace this line\n",
+        "        state_values_new[state] = 0\n",
+        "\n",
         "    return state_values_new\n",
         "\n",
         "# Greedily choose the action that maximizes the value for each state.\n",
@@ -527,4 +530,4 @@
       }
     }
   ]
-}
+}