Offline Reinforcement Learning on OGBench antmaze-large-stitch-singletask-task1
79Test ReturnBiTrajDiff
Evaluation Results
| Method | Links | |
|---|---|---|
| BiTrajDiffBase RL Algorithm=FQL, Data Augmentation Method=Ours2025.06 | 79 | |
| SSDBase RL Algorithm=FQL, Data Augmentation Method=SSD2025.06 | 75 | |
| BiTrajDiffBase RL Algorithm=IQL, Data Augmentation Method=Ours2025.06 | 64 | |
| ASTROBase RL Algorithm=FQL, Data Augmentation Method=ASTRO2025.06 | 57.3 | |
| SSDBase RL Algorithm=IQL, Data Augmentation Method=SSD2025.06 | 53 | |
| ASTROBase RL Algorithm=IQL, Data Augmentation Method=ASTRO2025.06 | 51.7 | |
| DiffStitchBase RL Algorithm=IQL, Data Augmentation Method=DiffStitch2025.06 | 35 | |
| DiffStitchBase RL Algorithm=FQL, Data Augmentation Method=DiffStitch2025.06 | 33.1 | |
| SyntherBase RL Algorithm=IQL, Data Augmentation Method=Synther2025.06 | 31.1 | |
| FQLBase RL Algorithm=FQL, Data Augmentation Method=Base2025.06 | 29.2 | |
| SyntherBase RL Algorithm=FQL, Data Augmentation Method=Synther2025.06 | 28.7 | |
| IQLBase RL Algorithm=IQL, Data Augmentation Method=Base2025.06 | 26.2 |