Offline Reinforcement Learning on D4RL MuJoCo walker2d-medium-replay v0
42.6Normalized ScoreFisherBRC
Evaluation Results
| Method | Links | |
|---|---|---|
| FisherBRCrandom seeds=5, evaluations=final 102022.06 | 42.6 | |
| MOPOrandom seeds=5, evaluations=final 102022.06 | 39 | |
| CABI+TD3_BCrandom seeds=5, evaluations=final 102022.06 | 29.4 | |
| TD3_BCrandom seeds=5, evaluations=final 102022.06 | 25.2 | |
| CQLrandom seeds=5, evaluations=final 102022.06 | 15.8 | |
| BCQrandom seeds=5, evaluations=final 102022.06 | 15 | |
| UWACrandom seeds=5, evaluations=final 102022.06 | 8.4 | |
| BCrandom seeds=5, evaluations=final 102022.06 | 8.3 |