Unsupervised Reinforcement Learning on ExORL quadruped zero-shot
645Average ReturnOne-Step FB
Evaluation Results
| Method | Links | |
|---|---|---|
| One-Step FBevaluation_mode=Zero-shot evaluation2026.02 | 645 | |
| ICVFevaluation_mode=Zero-shot evaluation2026.02 | 546 | |
| BYOL-gammaevaluation_mode=Zero-shot evaluation2026.02 | 496 | |
| Laplacianevaluation_mode=Zero-shot evaluation2026.02 | 462 | |
| HILPevaluation_mode=Zero-shot evaluation2026.02 | 352 | |
| FBevaluation_mode=Zero-shot evaluation2026.02 | 246 |