Reinforcement Learning on ZonesEnv
23.23RewardPPO-Lagrangian
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| PPO-Lagrangian2026.03 | 23.23 | 6 | 0 | |
| PPO-LTL-B2026.03 | 18.61 | 4.7 | 0.0018 | |
| PPO2026.03 | 17.95 | 3.7 | — | |
| PPO-LTL-A2026.03 | 17.86 | 4.3 | 0.0048 | |
| PPO-Shielding2026.03 | 15.92 | 12 | — | |
| PPO-Mask2026.03 | 10.14 | 6 | — |