Minor change on greedy policy variable usage

Chap 18, why not using directly the 'n_outputs' variable defined earlier, instead of hardcoded '2'
vvaezian · Feb 28, 2021 · 64f0e05 · 64f0e05
1 parent 0eb31f7
commit 64f0e05
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/18_reinforcement_learning.ipynb b/18_reinforcement_learning.ipynb
@@ -1306,7 +1306,7 @@
    "source": [
     "def epsilon_greedy_policy(state, epsilon=0):\n",
     "    if np.random.rand() < epsilon:\n",
-    "        return np.random.randint(2)\n",
+    "        return np.random.randint(n_outputs)\n",
     "    else:\n",
     "        Q_values = model.predict(state[np.newaxis])\n",
     "        return np.argmax(Q_values[0])"