hierarchical RL framework with inner-loop dynamics estimator
| Method | Links | ||||
|---|---|---|---|---|---|
| 0.151 | 95 | - | - | ||
| 0.18 | 95 | - | - | ||
2026.06 | 0.195 | 95 | - | - | |
| 0.195 | 95 | - | - | ||
| 0.205 | 90 | - | - | ||
2026.06 | 0.21 | 95 | - | - | |
2026.06 | 0.22 | 90 | - | - | |
2026.06 | 0.242 | 85 | - | - | |
2026.06 | 0.285 | 85 | - | - | |
2026.06 | 0.288 | 75 | - | - | |
2026.06 | 0.315 | 70 | - | - | |
2026.06 | 0.392 | 60 | - | - | |
2026.06 | - | - | 0.062 | 0 | |
2026.06 | - | - | 0.038 | 26.4 | |
| - | - | 0.024 | 40.9 |