Safe Reinforcement Learning on Bullet Safety Gym BallRun
579.5RewardPPO-Lagrangian
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| PPO-LagrangianKnowledge Level=Oracle2025.04 | 579.5 | 17.8 | — | |
| C-T BaselineKnowledge Level=Zero Knowledge2025.04 | 485.8 | 35.3 | 6,000 | |
| TraCeSKnowledge Level=Zero Knowledge2025.04 | 457 | 24.7 | 2,627 | |
| CPPO-PIDKnowledge Level=Oracle2025.04 | 455.2 | 3.7 | — |