Safe Reinforcement Learning on Safety Gym and Safe Racing
1Constraint Violation Rate 1PPO-Lag
Evaluation Results
| Method | Links | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| PPO-Lag2022.01 | 1 | 11 | 0 | 1 | 0 | 13 | 3 | 0 | 9 | 1 | 4 | 4 | 5 | 2 | 4 | |
| SAC2022.01 | 2 | 2 | 1 | 1 | 1 | 5 | 2 | 1 | 4 | 1 | 1 | 14 | 3 | 3 | 3 | |
| FOCOPS2022.01 | 3 | 28 | 16 | 21 | 10 | 16 | 12 | 10 | 23 | 32 | 10 | 1 | 26 | 9 | 11 | |
| SAC-actor2x-Lag2022.01 | 74 | 63 | 70 | 59 | 100 | 81 | 60 | 100 | 89 | 37 | 94 | 64 | 37 | 8 | 67 | |
| SEditor2022.01 | 101 | 94 | 78 | 149 | 99 | 95 | 155 | 100 | 100 | 178 | 100 | 100 | 128 | 57 | 110 |