Offline Reinforcement Learning on D4RL MuJoCo hopper medium-replay v0
67.5Normalized Avg ScoreMOPO
Evaluation Results
| Method | Links | |
|---|---|---|
| MOPOrandom seeds=5, evaluations=final 102022.06 | 67.5 | |
| FisherBRCrandom seeds=5, evaluations=final 102022.06 | 35.6 | |
| BCQrandom seeds=5, evaluations=final 102022.06 | 33.1 | |
| TD3_BCrandom seeds=5, evaluations=final 102022.06 | 31.4 | |
| CABI+TD3_BCrandom seeds=5, evaluations=final 102022.06 | 31.3 | |
| CQLrandom seeds=5, evaluations=final 102022.06 | 28.6 | |
| BCrandom seeds=5, evaluations=final 102022.06 | 19.7 | |
| UWACrandom seeds=5, evaluations=final 102022.06 | 18 |