Point Push on Safety Gymnasium level-2
0.33Safe RewardSB-TRPO
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| SB-TRPO2025.12 | 0.33 | 79 | 0.43 | 8 | |
| P3O2025.12 | 0.23 | 78 | 0.3 | 15 | |
| CUP2025.12 | 0.12 | 67 | 0.18 | 25 | |
| C3PO2025.12 | -0.15 | 85 | -0.18 | 6.3 | |
| FOCOPS2025.12 | -0.2 | 66 | -0.29 | 35 | |
| PPO-Lag2025.12 | -0.29 | 59 | -0.47 | 27 | |
| RCPO2025.12 | -0.48 | 84 | -0.57 | 6.3 | |
| TRPO-Lag2025.12 | -0.49 | 78 | -0.65 | 9.3 | |
| PCPO2025.12 | -1.1 | 79 | -1.4 | 14 | |
| CPO2025.12 | -1.2 | 77 | -1.6 | 5.8 | |
| C-TRPO2025.12 | -1.4 | 83 | -1.7 | 7.8 | |
| CPPO-PID2025.12 | -2.7 | 79 | -3.4 | 13 |