Offline Reinforcement Learning on Rotational Reacher Expert
99ReturnAug-D-Online
Evaluation results
| Method | Links | |
|---|---|---|
| Aug-D-OnlineAlgorithm=IQL, Zero-shot Policy Transfer=true, Rotation Group=C4 (90°)2026.07 | 99 | |
| DAC-OutputAlgorithm=IQL, Zero-shot Policy Transfer=true, Rotation Group=C4 (90°)2026.07 | 98 | |
| DAC-LatentAlgorithm=IQL, Zero-shot Policy Transfer=true, Rotation Group=C4 (90°)2026.07 | 95 | |
| Aug-DAlgorithm=IQL, Zero-shot Policy Transfer=true, Rotation Group=C4 (90°)2026.07 | 94 | |
| No DAAlgorithm=IQL, Zero-shot Policy Transfer=true, Data Augmentation=None2026.07 | 49 |