Reinforcement Learning on Humanoid
90,921,063Zero-Shot Reward
Open-Ended Neural Reward Functions
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| 90,921,063 | - | ||
2026.01 | 4,625 | - | |
2026.01 | 4,539 | - | |
2026.01 | 3,175 | - | |
2026.01 | 3,105 | - | |
2026.02 | 386.75 | - | |
2026.02 | 379.75 | - | |
2026.02 | 371.75 | - | |
2026.02 | 337.23 | - | |
2026.02 | 326.61 | - | |
2026.02 | 295.94 | - | |
2026.01 | 260.8 | - | |
2026.02 | 73.39 | - | |
2026.02 | 39.28 | - | |
2026.02 | 2.28 | - | |
2026.02 | 2.24 | - | |
2026.02 | 2.12 | - | |
2026.02 | 2.11 | - | |
2026.02 | 1.81 | - | |
2026.02 | 1.59 | - | |
2026.02 | 1.39 | - | |
2026.02 | 1.33 | - | |
2026.02 | 1.3 | - | |
2026.02 | 1.28 | - | |
2026.02 | 1.18 | - | |
2026.02 | 1.17 | - | |
2026.02 | 1.16 | - | |
2026.02 | 1.11 | - | |
2026.02 | 1.08 | - | |
2026.02 | 1.04 | - |