From 64f0e05a941897d3475c2f4cce7ca573f68daac4 Mon Sep 17 00:00:00 2001
From: B D <73541689+lebaste77@users.noreply.github.com>
Date: Sun, 28 Feb 2021 12:02:23 +0100
Subject: [PATCH] Minor change on greedy policy variable usage

Chap 18, why not using directly the 'n_outputs' variable defined earlier, instead of hardcoded '2'
---
 18_reinforcement_learning.ipynb | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/18_reinforcement_learning.ipynb b/18_reinforcement_learning.ipynb
index ed44866..b723f04 100644
--- 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])"