[BugFix] adapt log-prob TD batch-size to advantage shape in PPO #4225
Job | Run time |
---|---|
39m 14s | |
38m 11s | |
40m 30s | |
40m 10s | |
40m 22s | |
1h 4m 17s | |
51m 15s | |
40m 45s | |
1h 5m 30s | |
7h 0m 14s |
Job | Run time |
---|---|
39m 14s | |
38m 11s | |
40m 30s | |
40m 10s | |
40m 22s | |
1h 4m 17s | |
51m 15s | |
40m 45s | |
1h 5m 30s | |
7h 0m 14s |