arthur/handson-ml3
1
0
Fork 0
mirror of https://github.com/ArthurDanjou/handson-ml3.git synced 2026-01-25 01:10:29 +01:00
Code Issues Packages Projects Releases Wiki Activity

Minor change on greedy policy variable usage

Browse Source 
Chap 18, why not using directly the 'n_outputs' variable defined earlier, instead of hardcoded '2'
This commit is contained in:
B D
2021-02-28 12:02:23 +01:00
committed by GitHub
parent 0eb31f77c2
commit 64f0e05a94
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
18_reinforcement_learning.ipynb
View File

@@ -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])"