Car Circle on Safety Gymnasium level-2
11Safe RewardTRPO-Lag
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| TRPO-Lag2025.12 | 11 | 0.81 | 13 | 18 | |
| PCPO2025.12 | 11 | 0.89 | 12 | 4.4 | |
| RCPO2025.12 | 10 | 0.9 | 11 | 13 | |
| FOCOPS2025.12 | 8.1 | 0.96 | 8.4 | 3.9 | |
| SB-TRPO2025.12 | 7.5 | 0.99 | 7.5 | 0.28 | |
| PPO-Lag2025.12 | 7.5 | 0.86 | 8.7 | 22 | |
| CUP2025.12 | 7.1 | 0.75 | 9.6 | 48 | |
| P3O2025.12 | 7.1 | 0.94 | 7.6 | 11 | |
| C3PO2025.12 | 5.1 | 0.99 | 5.1 | 0.53 | |
| CPO2025.12 | 0.96 | 0.99 | 0.96 | 0.98 | |
| CPPO-PID2025.12 | 0.96 | 0.91 | 1.3 | 27 | |
| C-TRPO2025.12 | 0.54 | 0.97 | 0.56 | 3.9 |