Offline Reinforcement Learning on D4RL MuJoCo walker2d-medium v0
82Normalized ScoreCABI+TD3_BC
Evaluation Results
| Method | Links | |
|---|---|---|
| CABI+TD3_BCrandom seeds=5, evaluations=final 102022.06 | 82 | |
| TD3_BCrandom seeds=5, evaluations=final 102022.06 | 79.7 | |
| FisherBRCrandom seeds=5, evaluations=final 102022.06 | 79.5 | |
| CQLrandom seeds=5, evaluations=final 102022.06 | 57.5 | |
| BCQrandom seeds=5, evaluations=final 102022.06 | 53.1 | |
| MOPOrandom seeds=5, evaluations=final 102022.06 | 17.8 | |
| UWACrandom seeds=5, evaluations=final 102022.06 | 17.4 | |
| BCrandom seeds=5, evaluations=final 102022.06 | 11.4 |