[BugFix] adapt log-prob TD batch-size to advantage shape in PPO #47
Job | Run time |
---|---|
7s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
1s | |
14s | |
13s | |
13s | |
9s | |
13s | |
10s | |
13s | |
9s | |
10s | |
7s | |
16s | |
17s | |
14s | |
8s | |
9s | |
15s | |
10s | |
9s | |
13s | |
15s | |
8s | |
8s | |
9s | |
7s | |
11s | |
15s | |
17s | |
9s | |
9s | |
15s | |
8s | |
14s | |
9s | |
8s | |
14s | |
7m 20s |