Safe Reinforcement Learning on Bullet Safety Gym CarRun
577.7RewardPPO-Lagrangian
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| PPO-LagrangianKnowledge Level=Oracle2025.04 | 577.7 | 22 | — | |
| FOCOPSKnowledge Level=Oracle2025.04 | 573.7 | 44.9 | — | |
| C-T BaselineKnowledge Level=Zero Knowledge2025.04 | 569.1 | 13.3 | 6,000 | |
| TraCeSKnowledge Level=Zero Knowledge2025.04 | 568.3 | 23.3 | 8,832 | |
| TraCeSKnowledge Level=Zero Knowledge2025.04 | 568.3 | 23.3 | 8,832 | |
| CPPO-PIDKnowledge Level=Oracle2025.04 | 568.2 | 14.8 | — | |
| CUPKnowledge Level=Oracle2025.04 | 567.8 | 6.9 | — | |
| TRPO-SauteKnowledge Level=Oracle2025.04 | 552 | 22.4 | — |