Unsupervised Reinforcement Learning on ExORL Walker (4 Tasks) (Zero-Shot)
619Average ReturnICVF
Evaluation Results
| Method | Links | |
|---|---|---|
| ICVFevaluation_mode=Zero-shot evaluation2026.02 | 619 | |
| FBevaluation_mode=Zero-shot evaluation2026.02 | 400 | |
| HILPevaluation_mode=Zero-shot evaluation2026.02 | 393 | |
| One-Step FBevaluation_mode=Zero-shot evaluation2026.02 | 379 | |
| Laplacianevaluation_mode=Zero-shot evaluation2026.02 | 228 | |
| BYOL-gammaevaluation_mode=Zero-shot evaluation2026.02 | 227 |