Reinforcement Learning Control on ManiSkill2 pick-cube
161ReturnClean
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Clean2026.06 | 161 | 0.028 | — | — | — | |
| SWAAP (Random)alpha=0.9, rp=0.12026.06 | 158 | — | 0.029 | 0.026 | — | |
| SWAAPalpha=0.9, rp=0.12026.06 | 147 | — | 0.069 | 0.027 | 0.025 | |
| Direct Model Poisoning2026.06 | 117 | — | 0.198 | — | — |