Offline Reinforcement Learning on D4RL MuJoCo walker2d-medium-expert v0
108.4Normalized ScoreCABI+TD3_BC
Evaluation results
| Method | Links | |
|---|---|---|
| CABI+TD3_BCrandom seeds=5, evaluations=final 102022.06 | 108.4 | |
| FisherBRCrandom seeds=5, evaluations=final 102022.06 | 103.6 | |
| TD3_BCrandom seeds=5, evaluations=final 102022.06 | 101.1 | |
| CQLrandom seeds=5, evaluations=final 102022.06 | 68.1 | |
| BCQrandom seeds=5, evaluations=final 102022.06 | 57.5 | |
| MOPOrandom seeds=5, evaluations=final 102022.06 | 44.6 | |
| UWACrandom seeds=5, evaluations=final 102022.06 | 14.8 | |
| BCrandom seeds=5, evaluations=final 102022.06 | 12 |