Offline Reinforcement Learning on D4RL MuJoCo halfcheetah-medium-replay v0
53.1Normalized ScoreMOPO
Evaluation Results
| Method | Links | |
|---|---|---|
| MOPOrandom seeds=5, evaluations=final 102022.06 | 53.1 | |
| CABI+TD3_BCrandom seeds=5, evaluations=final 102022.06 | 44.4 | |
| TD3_BCrandom seeds=5, evaluations=final 102022.06 | 43.3 | |
| FisherBRCrandom seeds=5, evaluations=final 102022.06 | 43.3 | |
| CQLrandom seeds=5, evaluations=final 102022.06 | 41.9 | |
| UWACrandom seeds=5, evaluations=final 102022.06 | 38.9 | |
| BCQrandom seeds=5, evaluations=final 102022.06 | 38.2 | |
| BCrandom seeds=5, evaluations=final 102022.06 | 34.7 |