Stack on ManiSkill 3
95.2Success at Endpi_0.5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| pi_0.5Optimization Strategy=GTP-FA2026.06 | 95.2 | — | |
| pi_0.5Optimization Strategy=112026.06 | 92.4 | — | |
| pi_0.5Optimization Strategy=002026.06 | 89.4 | — | |
| PPOOptimization Strategy=GTP-FA2026.06 | 80.7 | 90.4 | |
| BCOptimization Strategy=GTP-FA2026.06 | 69.6 | 84.5 | |
| PPOOptimization Strategy=112026.06 | 68.7 | 86.4 | |
| SACOptimization Strategy=GTP-FA2026.06 | 53.6 | 65.1 | |
| PPOOptimization Strategy=012026.06 | 42.8 | 52.1 | |
| pi_0.5Optimization Strategy=012026.06 | 36.2 | — | |
| PPOOptimization Strategy=002026.06 | 29.1 | 65.2 | |
| SACOptimization Strategy=002026.06 | 14.3 | 22.8 | |
| BCOptimization Strategy=112026.06 | 14.2 | 24.2 | |
| SACOptimization Strategy=112026.06 | 13.2 | 26.6 | |
| SACOptimization Strategy=012026.06 | 9.8 | 17.6 | |
| PPOOptimization Strategy=102026.06 | 9.4 | 23.2 | |
| SACOptimization Strategy=102026.06 | 7.7 | 18.4 | |
| DPOptimization Strategy=GTP-FA2026.06 | 5.5 | 7.1 | |
| DPOptimization Strategy=012026.06 | 4.3 | 7.2 | |
| DPOptimization Strategy=112026.06 | 3.4 | 6.3 | |
| BCOptimization Strategy=002026.06 | 0 | 0 | |
| DPOptimization Strategy=002026.06 | 0 | 0 | |
| BCOptimization Strategy=012026.06 | 0 | 0 | |
| BCOptimization Strategy=102026.06 | 0 | 0 | |
| DPOptimization Strategy=102026.06 | 0 | 0 | |
| pi_0.5Optimization Strategy=102026.06 | 0 | — |