Offline Reinforcement Learning on D4RL kitchen-mixed
37Test ReturnBiTrajDiff
Evaluation Results
| Method | Links | |
|---|---|---|
| BiTrajDiffAlgorithm=DT, Augmentation Method=Ours2025.06 | 37 | |
| SyntherAlgorithm=DT, Augmentation Method=Synther2025.06 | 31.6 | |
| DiffStitchAlgorithm=DT, Augmentation Method=DiffStitch2025.06 | 24.7 | |
| RTDiffAlgorithm=DT, Augmentation Method=RTDiff2025.06 | 23.7 | |
| BaseAlgorithm=DT, Augmentation Method=Base2025.06 | 22.5 | |
| BiTrajDiffAlgorithm=CQL, Augmentation Method=Ours2025.06 | 21.5 | |
| SyntherAlgorithm=CQL, Augmentation Method=Synther2025.06 | 19.3 | |
| RTDiffAlgorithm=CQL, Augmentation Method=RTDiff2025.06 | 19.1 | |
| BaseAlgorithm=CQL, Augmentation Method=Base2025.06 | 16.2 | |
| DiffStitchAlgorithm=CQL, Augmentation Method=DiffStitch2025.06 | 12 |