Offline Reinforcement Learning on D4RL MuJoCo hopper expert v0
112.4Normalized Average ScoreCABI+TD3_BC
Evaluation results
| Method | Links | |
|---|---|---|
| CABI+TD3_BCrandom seeds=5, evaluations=final 102022.06 | 112.4 | |
| FisherBRCrandom seeds=5, evaluations=final 102022.06 | 112.3 | |
| TD3_BCrandom seeds=5, evaluations=final 102022.06 | 112.2 | |
| BCrandom seeds=5, evaluations=final 102022.06 | 111.5 | |
| CQLrandom seeds=5, evaluations=final 102022.06 | 111.2 | |
| UWACrandom seeds=5, evaluations=final 102022.06 | 109.1 | |
| BCQrandom seeds=5, evaluations=final 102022.06 | 107 |