Offline Reinforcement Learning on D4RL MuJoCo halfcheetah-medium v0
45.1Normalized ScoreCABI+TD3_BC
Evaluation Results
| Method | Links | |
|---|---|---|
| CABI+TD3_BCrandom seeds=5, evaluations=final 102022.06 | 45.1 | |
| TD3_BCrandom seeds=5, evaluations=final 102022.06 | 42.8 | |
| MOPOrandom seeds=5, evaluations=final 102022.06 | 42.3 | |
| FisherBRCrandom seeds=5, evaluations=final 102022.06 | 41.3 | |
| BCQrandom seeds=5, evaluations=final 102022.06 | 40.7 | |
| UWACrandom seeds=5, evaluations=final 102022.06 | 37.4 | |
| CQLrandom seeds=5, evaluations=final 102022.06 | 37.2 | |
| BCrandom seeds=5, evaluations=final 102022.06 | 36.6 |