Unsupervised Reinforcement Learning on ExORL quadruped zero-shot
645Average Return
One-Step FB
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 645 | |
2026.02 | 546 | |
2026.02 | 496 | |
2026.02 | 462 | |
2026.02 | 352 | |
2026.02 | 246 |
One-Step FB
| Method | Links | |
|---|---|---|
2026.02 | 645 | |
2026.02 | 546 | |
2026.02 | 496 | |
2026.02 | 462 | |
2026.02 | 352 | |
2026.02 | 246 |