Walker2d Control on MuJoCo (eval)
2,797.7RewardRLSF
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| RLSFKnowledge Level=Partial Knowledge2025.04 | 2,797.7 | 0.3 | 15,227 | |
| PPO-LagrangianKnowledge Level=Oracle2025.04 | 2,682.2 | 10.3 | — | |
| CPPO-PIDKnowledge Level=Oracle2025.04 | 2,562.8 | 14 | — | |
| C-T BaselineKnowledge Level=Zero Knowledge2025.04 | 2,491 | 16.7 | 6,000 | |
| TraCeSKnowledge Level=Zero Knowledge2025.04 | 2,211.2 | 24.1 | 5,735 |