113c1d84a806358d5c9f1242a88edb3966a304ab,ch09/04_pong_pg.py,,,#,47
Before Change
batch_scales.append(exp.reward)
// handle new rewards
new_rewards = exp_source.pop_total_rewards()
if new_rewards and tracker.reward(new_rewards[0], step_idx) :
break
if len(batch_states) < BATCH_SIZE:After Change
batch_scales.append(exp.reward)
// handle new rewards
new_rewards = exp_source.pop_total_rewards()
if new_rewards :
if tracker.reward(new_rewards[0], step_idx) :
break
if len(batch_states) < BATCH_SIZE:In pattern: SUPERPATTERN
Frequency: 3
Non-data size: 3
Instances Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 113c1d84a806358d5c9f1242a88edb3966a304ab
Time: 2017-12-05
Author: max.lapan@gmail.com
File Name: ch09/04_pong_pg.py
Class Name:
Method Name:
Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 1143605d2ac3a46f50a218b8219633b633d2e697
Time: 2018-02-03
Author: max.lapan@gmail.com
File Name: ch14/02_train_a2c.py
Class Name:
Method Name:
Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: a868c6dd92867f17a5b1c56299d445b0a115dcac
Time: 2018-02-09
Author: max.lapan@gmail.com
File Name: ch15/01_train_a2c.py
Class Name:
Method Name:
