Reinforcement Learning Control on Meta-World soccer
1,724ReturnClean
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Clean2026.06 | 1,724 | 0.033 | — | — | — | |
| SWAAP (Random)alpha=0.9, rp=0.12026.06 | 1,711 | — | 0.034 | 0.05 | — | |
| Direct Model Poisoning2026.06 | 1,555 | — | 0.083 | — | — | |
| SWAAPalpha=0.9, rp=0.12026.06 | 1,479 | — | 0.064 | 0.051 | 0.046 |