Reinforcement Learning Control on DMControl dog-walk
798ReturnClean
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Clean2026.06 | 798 | 5.6 | — | — | — | |
| SWAAP (Random)alpha=0.9, rp=0.12026.06 | 794 | — | 5.5 | 5.9 | — | |
| SWAAPalpha=0.9, rp=0.12026.06 | 748 | — | 6.1 | 6 | 5.9 | |
| Direct Model Poisoning2026.06 | 523 | — | 8.6 | — | — |