Offline Reinforcement Learning on D4RL Adroit pen-cloned v1
92.8Normalized ScoreIPD
Evaluation results
| Method | Links | |
|---|---|---|
| IPDEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 92.8 | |
| QTEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 90.1 | |
| ReinformerEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 82.4 | |
| DTEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 75.8 | |
| QDTEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 64.2 | |
| EDTEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 48.4 | |
| DDEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 42.8 | |
| CQLEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 39.2 | |
| IQLEvaluation Protocol=Tenfold Episode Evaluation2026.03 | 37.3 |