Offline Reinforcement Learning on D4RL MuJoCo hopper-medium v0
100.4Avg Score (Normalized)CABI+TD3_BC
Evaluation results
| Method | Links | |
|---|---|---|
| CABI+TD3_BCrandom seeds=5, evaluations=final 102022.06 | 100.4 | |
| TD3_BCrandom seeds=5, evaluations=final 102022.06 | 99.5 | |
| FisherBRCrandom seeds=5, evaluations=final 102022.06 | 99.4 | |
| BCQrandom seeds=5, evaluations=final 102022.06 | 54.5 | |
| CQLrandom seeds=5, evaluations=final 102022.06 | 44.2 | |
| UWACrandom seeds=5, evaluations=final 102022.06 | 30.3 | |
| BCrandom seeds=5, evaluations=final 102022.06 | 30 | |
| MOPOrandom seeds=5, evaluations=final 102022.06 | 28 |