Reinforcement Learning Control on DMControl cheetah-run
838ReturnClean
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Clean2026.06 | 838 | 2.6 | — | — | — | |
| SWAAP (Random)alpha=0.9, rp=0.12026.06 | 830 | — | 2.5 | 3.2 | — | |
| SWAAPalpha=0.9, rp=0.12026.06 | 806 | — | 3.6 | 3.4 | 2.8 | |
| Direct Model Poisoning2026.06 | 389 | — | 10.4 | — | — |