gaspersic/baselines
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #14 from quanvuong/master

Browse Source 
Consistent initial type (float) for episode_rewards
This commit is contained in:
Szymon Sidor
2017-06-04 00:40:42 -07:00
committed by GitHub
parent 9c10c2fc27 86054f7a98
commit 584261a94a
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
baselines/deepq/simple.py
View File

@@ -222,7 +222,7 @@ def learn(env,
episode_rewards[-1] += rew episode_rewards[-1] += rew
if done: if done:
obs = env.reset() obs = env.reset()
episode_rewards.append(0) episode_rewards.append(0.0)
if t > learning_starts and t % train_freq == 0: if t > learning_starts and t % train_freq == 0:
# Minimize the error in Bellman's equation on a batch sampled from replay buffer. # Minimize the error in Bellman's equation on a batch sampled from replay buffer.