Reinforcement Learning Control on DMControl dog-run
637ReturnClean
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Clean2026.06 | 637 | 0.052 | — | — | — | |
| SWAAP (Random)alpha=0.9, rp=0.12026.06 | 607 | — | 0.054 | 0.051 | — | |
| SWAAPalpha=0.9, rp=0.12026.06 | 478 | — | 0.064 | 0.052 | 0.051 | |
| Direct Model Poisoning2026.06 | 270 | — | 0.081 | — | — |