[BugFix] adapt log-prob TD batch-size to advantage shape in PPO #2074
Job | Run time |
---|---|
4s | |
4s | |
7m 57s | |
7m 57s | |
11m 4s | |
11m 4s | |
9m 48s | |
9m 48s | |
9m 49s | |
9m 49s | |
15s | |
12s | |
9s | |
9s | |
15s | |
16s | |
11s | |
16s | |
1h 19m 7s |
Job | Run time |
---|---|
4s | |
4s | |
7m 57s | |
7m 57s | |
11m 4s | |
11m 4s | |
9m 48s | |
9m 48s | |
9m 49s | |
9m 49s | |
15s | |
12s | |
9s | |
9s | |
15s | |
16s | |
11s | |
16s | |
1h 19m 7s |