Offline Reinforcement Learning on D4RL kitchen-complete
67.9Test ReturnBiTrajDiff
Evaluation results
| Method | Links | |
|---|---|---|
| BiTrajDiffAlgorithm=DT, Augmentation Method=Ours2025.06 | 67.9 | |
| DiffStitchAlgorithm=DT, Augmentation Method=DiffStitch2025.06 | 63.4 | |
| SyntherAlgorithm=DT, Augmentation Method=Synther2025.06 | 62.3 | |
| BaseAlgorithm=DT, Augmentation Method=Base2025.06 | 61.7 | |
| RTDiffAlgorithm=DT, Augmentation Method=RTDiff2025.06 | 61.3 | |
| RTDiffAlgorithm=CQL, Augmentation Method=RTDiff2025.06 | 15.2 | |
| BiTrajDiffAlgorithm=CQL, Augmentation Method=Ours2025.06 | 13.8 | |
| DiffStitchAlgorithm=CQL, Augmentation Method=DiffStitch2025.06 | 10.5 | |
| SyntherAlgorithm=CQL, Augmentation Method=Synther2025.06 | 8.4 | |
| BaseAlgorithm=CQL, Augmentation Method=Base2025.06 | 7.8 |