Offline Reinforcement Learning on D4RL MuJoCo hopper-medium-expert v0
112.7Normalized Avg ScoreCABI+TD3_BC
Evaluation Results
| Method | Links | |
|---|---|---|
| CABI+TD3_BCrandom seeds=5, evaluations=final 102022.06 | 112.7 | |
| TD3_BCrandom seeds=5, evaluations=final 102022.06 | 112.2 | |
| CQLrandom seeds=5, evaluations=final 102022.06 | 111.4 | |
| BCQrandom seeds=5, evaluations=final 102022.06 | 110.9 | |
| UWACrandom seeds=5, evaluations=final 102022.06 | 95.4 | |
| FisherBRCrandom seeds=5, evaluations=final 102022.06 | 90.6 | |
| BCrandom seeds=5, evaluations=final 102022.06 | 89.6 | |
| MOPOrandom seeds=5, evaluations=final 102022.06 | 23.7 |