PointCircle1 on Safety Gymnasium (eval)
46.8RewardCPPO-PID
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| CPPO-PIDKnowledge Level=Oracle2025.04 | 46.8 | 29.4 | — | |
| PPO-LagrangianKnowledge Level=Oracle2025.04 | 46.6 | 21.5 | — | |
| TraCeSKnowledge Level=Zero Knowledge2025.04 | 43.2 | 16.2 | 5,830 | |
| RLSFKnowledge Level=Partial Knowledge2025.04 | 41.9 | 1.6 | 3,244 | |
| C-T BaselineKnowledge Level=Zero Knowledge2025.04 | 40.2 | 25.3 | 12,000 |