Reinforcement Learning Control on DMControl humanoid-run
584ReturnClean
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Clean2026.06 | 584 | 0.049 | — | — | — | |
| SWAAP (Random)alpha=0.9, rp=0.12026.06 | 567 | — | 0.053 | 0.052 | — | |
| SWAAPalpha=0.9, rp=0.12026.06 | 515 | — | 0.063 | 0.053 | 0.051 | |
| Direct Model Poisoning2026.06 | 189 | — | 0.104 | — | — |