Offline Reinforcement Learning on D4RL MuJoCo halfcheetah-expert v0
107.6Normalized ScoreCABI+TD3_BC
Evaluation Results
| Method | Links | |
|---|---|---|
| CABI+TD3_BCrandom seeds=5, evaluations=final 102022.06 | 107.6 | |
| FisherBRCrandom seeds=5, evaluations=final 102022.06 | 106.8 | |
| TD3_BCrandom seeds=5, evaluations=final 102022.06 | 105.7 | |
| BCrandom seeds=5, evaluations=final 102022.06 | 105.2 | |
| UWACrandom seeds=5, evaluations=final 102022.06 | 104 | |
| BCQrandom seeds=5, evaluations=final 102022.06 | 89.9 | |
| CQLrandom seeds=5, evaluations=final 102022.06 | 82.4 |