CarCircle2 on Safety Gymnasium (val)
16.2RewardPPO-Lagrangian
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| PPO-LagrangianKnowledge Level=Oracle2025.04 | 16.2 | 28.3 | — | |
| C-T BaselineKnowledge Level=Zero Knowledge2025.04 | 15.3 | 44 | 12,000 | |
| TraCeSKnowledge Level=Zero Knowledge2025.04 | 15.2 | 11.9 | 4,341 | |
| CPPO-PIDKnowledge Level=Oracle2025.04 | 14.9 | 22.6 | — | |
| RLSFKnowledge Level=Partial Knowledge2025.04 | 13.7 | 20.2 | 7,601 |