Goal2 on Safety Gymnasium
11.48RewardSC
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SCchi=5.02025.10 | 11.48 | 31.2 | |
| USCchi=5.0, Refinement=Refined2025.10 | 9.48 | 20.3 | |
| CSCchi=5.02025.10 | 9.44 | 27 | |
| USC (NR)chi=5.0, Refinement=None2025.10 | 9.38 | 26.3 | |
| DDPGchi=5.02025.10 | 9.13 | 41.8 | |
| USCCost Limit (chi)=5.02025.10 | 8.84 | 5.05 | |
| DDPGCost Limit (chi)=5.02025.10 | 8.74 | 5.36 | |
| CPOCost Limit (chi)=5.02025.10 | 8.74 | 5.08 | |
| USC (NR)Cost Limit (chi)=5.02025.10 | 8.74 | 5.53 | |
| PID-Lagchi=5.02025.10 | 8.73 | 25.1 | |
| CSCCost Limit (chi)=5.02025.10 | 8.65 | 5.28 | |
| RCPOCost Limit (chi)=5.02025.10 | 8.28 | 5.13 | |
| CPOchi=5.02025.10 | 8.04 | 21.5 | |
| RCPOchi=5.02025.10 | 8.02 | 33.2 | |
| SCCost Limit (chi)=5.02025.10 | 7.54 | 5.65 | |
| PID-LagCost Limit (chi)=5.02025.10 | 5.88 | 4.94 |