Offline Reinforcement Learning on D4RL MuJoCo halfcheetah-random v0
35.4Normalized Average ScoreMOPO
Evaluation Results
| Method | Links | |
|---|---|---|
| MOPOrandom seeds=5, evaluations=final 102022.06 | 35.4 | |
| FisherBRCrandom seeds=5, evaluations=final 102022.06 | 32.2 | |
| CQLrandom seeds=5, evaluations=final 102022.06 | 21.7 | |
| CABI+TD3_BCrandom seeds=5, evaluations=final 102022.06 | 15.1 | |
| TD3_BCrandom seeds=5, evaluations=final 102022.06 | 10.2 | |
| UWACrandom seeds=5, evaluations=final 102022.06 | 2.3 | |
| BCQrandom seeds=5, evaluations=final 102022.06 | 2.2 | |
| BCrandom seeds=5, evaluations=final 102022.06 | 2 |