Reinforcement Learning on Walker Run
34.97Mean PerformanceFLAM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FLAMlatent actions=82026.06 | 34.97 | 9.15 | |
| OTF-LAM-DINO2026.06 | 28.87 | 8.23 | |
| LAPO2026.06 | 28.71 | 7.59 | |
| FLAMlatent actions=42026.06 | 27.61 | 7.22 | |
| OTF-LAM2026.06 | 26.94 | 7.91 | |
| HiLAM2026.06 | 25.12 | 5.88 | |
| Motion LAPO2026.06 | 23.93 | 4.4 | |
| F-LAPO2026.06 | 23.44 | 5.79 |