diff --git a/FA/Q-Learning with Value Function Approximation Solution.ipynb b/FA/Q-Learning with Value Function Approximation Solution.ipynb
index a271d6a63..40d843157 100644
--- a/FA/Q-Learning with Value Function Approximation Solution.ipynb	
+++ b/FA/Q-Learning with Value Function Approximation Solution.ipynb	
@@ -171,7 +171,7 @@
     "    \n",
     "    \"\"\"\n",
     "    def policy_fn(observation):\n",
-    "        A = np.ones(nA, dtype=float) * epsilon / nA\n",
+    "        A = np.ones(nA, dtype=float) * epsilon / (nA - 1)\n",
     "        q_values = estimator.predict(observation)\n",
     "        best_action = np.argmax(q_values)\n",
     "        A[best_action] += (1.0 - epsilon)\n",
@@ -369,22 +369,23 @@
   }
  ],
  "metadata": {
+  "anaconda-cloud": {},
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python [conda root]",
    "language": "python",
-   "name": "python3"
+   "name": "conda-root-py"
   },
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 3
+    "version": 2
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.5.1"
+   "pygments_lexer": "ipython2",
+   "version": "2.7.12"
   }
  },
  "nbformat": 4,