CarCircle1 on Safety Gymnasium (val)
18.3RewardPPO-Lagrangian
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| PPO-LagrangianKnowledge Level=Oracle2025.04 | 18.3 | 23.5 | — | |
| C-T BaselineKnowledge Level=Zero Knowledge2025.04 | 18 | 28.2 | 12,000 | |
| CPPO-PIDKnowledge Level=Oracle2025.04 | 17.9 | 23.7 | — | |
| TraCeSKnowledge Level=Zero Knowledge2025.04 | 17.4 | 11.3 | 4,005 | |
| RLSFKnowledge Level=Partial Knowledge2025.04 | 14.3 | 33.8 | 7,479 |