Offline Reinforcement Learning on D4RL Adroit hammer-human v1
2,480Normalized ScoreQT
Evaluation results
| Method | Links | |
|---|---|---|
| QTEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 2,480 | |
| IPDEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 2,290 | |
| ReinformerEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 1,720 | |
| EDTEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 1,420 | |
| QDTEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 680 | |
| CQLEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 440 | |
| DDEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 190 | |
| IQLEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 140 | |
| DTEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 20 |