Reinforcement Learning on Cheetah-Wind-S dynamics changes (time-step)
-42.3Average Return
Ada-Diffuser + DP (Oracle)
Updated 16d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.05 | -42.3 | |
2026.05 | -44.7 | |
2026.05 | -48 | |
2026.05 | -52.9 | |
2026.05 | -63.4 | |
2026.05 | -76.5 | |
2026.05 | -87.8 | |
2026.05 | -120.6 |