Offline Reinforcement Learning on D4RL MuJoCo halfcheetah-medium-expert v0
105Normalized ScoreCABI+TD3_BC
Evaluation Results
| Method | Links | |
|---|---|---|
| CABI+TD3_BCrandom seeds=5, evaluations=final 102022.06 | 105 | |
| TD3_BCrandom seeds=5, evaluations=final 102022.06 | 97.9 | |
| FisherBRCrandom seeds=5, evaluations=final 102022.06 | 96.1 | |
| BCrandom seeds=5, evaluations=final 102022.06 | 67.6 | |
| BCQrandom seeds=5, evaluations=final 102022.06 | 64.7 | |
| MOPOrandom seeds=5, evaluations=final 102022.06 | 63.3 | |
| UWACrandom seeds=5, evaluations=final 102022.06 | 40.6 | |
| CQLrandom seeds=5, evaluations=final 102022.06 | 27.1 |