Unsupervised Reinforcement Learning on ExORL Cheetah (zero-shot)
378Average ReturnOne-Step FB
Evaluation Results
| Method | Links | |
|---|---|---|
| One-Step FBevaluation_mode=Zero-shot evaluation2026.02 | 378 | |
| FBevaluation_mode=Zero-shot evaluation2026.02 | 271 | |
| ICVFevaluation_mode=Zero-shot evaluation2026.02 | 187 | |
| BYOL-gammaevaluation_mode=Zero-shot evaluation2026.02 | 127 | |
| Laplacianevaluation_mode=Zero-shot evaluation2026.02 | 125 | |
| HILPevaluation_mode=Zero-shot evaluation2026.02 | 116 |