Offline Reinforcement Learning on D4RL MuJoCo walker2d-random v0
13.6Normalized ScoreMOPO
Evaluation Results
| Method | Links | |
|---|---|---|
| MOPOrandom seeds=5, evaluations=final 102022.06 | 13.6 | |
| CABI+TD3_BCrandom seeds=5, evaluations=final 102022.06 | 6.4 | |
| BCQrandom seeds=5, evaluations=final 102022.06 | 4.9 | |
| UWACrandom seeds=5, evaluations=final 102022.06 | 3.8 | |
| CQLrandom seeds=5, evaluations=final 102022.06 | 2.7 | |
| TD3_BCrandom seeds=5, evaluations=final 102022.06 | 1.4 | |
| BCrandom seeds=5, evaluations=final 102022.06 | 1.2 | |
| FisherBRCrandom seeds=5, evaluations=final 102022.06 | 0.6 |