Offline Reinforcement Learning on OGBench cube-single-play-singletask-task1
98Test ReturnBiTrajDiff
Evaluation Results
| Method | Links | |
|---|---|---|
| BiTrajDiffBase RL Algorithm=FQL, Data Augmentation Method=Ours2025.06 | 98 | |
| SSDBase RL Algorithm=FQL, Data Augmentation Method=SSD2025.06 | 93 | |
| ASTROBase RL Algorithm=FQL, Data Augmentation Method=ASTRO2025.06 | 92.9 | |
| DiffStitchBase RL Algorithm=FQL, Data Augmentation Method=DiffStitch2025.06 | 89.6 | |
| ASTROBase RL Algorithm=IQL, Data Augmentation Method=ASTRO2025.06 | 89.2 | |
| FQLBase RL Algorithm=FQL, Data Augmentation Method=Base2025.06 | 88 | |
| SyntherBase RL Algorithm=FQL, Data Augmentation Method=Synther2025.06 | 87.3 | |
| BiTrajDiffBase RL Algorithm=IQL, Data Augmentation Method=Ours2025.06 | 87 | |
| SyntherBase RL Algorithm=IQL, Data Augmentation Method=Synther2025.06 | 82.4 | |
| SSDBase RL Algorithm=IQL, Data Augmentation Method=SSD2025.06 | 82 | |
| IQLBase RL Algorithm=IQL, Data Augmentation Method=Base2025.06 | 81.5 | |
| DiffStitchBase RL Algorithm=IQL, Data Augmentation Method=DiffStitch2025.06 | 79 |