CS_ALearn/deep-rl-class
1
0
Fork 0
mirror of https://github.com/huggingface/deep-rl-class.git synced 2026-04-13 16:49:44 +08:00
Code Issues Projects Releases Wiki Activity

Revert "Fix bug with agent evaluation for very long episodes"

Browse Source 
This reverts commit 591c8ccb75, reversing
changes made to f74adfb0a2.
This commit is contained in:
Thomas Simonini
2022-05-29 15:27:59 +02:00
parent 16a76eb540
commit baef4733c1
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
unit2/unit2.ipynb
View File

@@ -901,9 +901,9 @@
" total_rewards_ep += reward\n",
" \n",
" if done:\n",
" episode_rewards.append(total_rewards_ep)\n",
" break\n",
" state = new_state\n",
" episode_rewards.append(total_rewards_ep)\n",
" mean_reward = np.mean(episode_rewards)\n",
" std_reward = np.std(episode_rewards)\n",
"\n",