Offline Reinforcement Learning on D4RL MuJoCo walker2d-expert v0
108.6Normalized Avg ScoreCABI+TD3_BC
Evaluation Results
| Method | Links | |
|---|---|---|
| CABI+TD3_BCrandom seeds=5, evaluations=final 102022.06 | 108.6 | |
| TD3_BCrandom seeds=5, evaluations=final 102022.06 | 105.7 | |
| CQLrandom seeds=5, evaluations=final 102022.06 | 103.8 | |
| BCQrandom seeds=5, evaluations=final 102022.06 | 102.3 | |
| UWACrandom seeds=5, evaluations=final 102022.06 | 88.4 | |
| FisherBRCrandom seeds=5, evaluations=final 102022.06 | 79.9 | |
| BCrandom seeds=5, evaluations=final 102022.06 | 56 |