Constrained Reinforcement Learning on MuJoCo Ant (eval)
3,177.6RewardFOCOPS
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| FOCOPSKnowledge Level=Oracle2025.04 | 3,177.6 | 12.7 | — | |
| CUPKnowledge Level=Oracle2025.04 | 3,119.7 | 5.1 | — | |
| TRPO-SauteKnowledge Level=Oracle2025.04 | 3,102 | 17 | — | |
| TraCeSKnowledge Level=Zero Knowledge2025.04 | 2,885.4 | 19.5 | 4,657 |