Reinforcement Learning on obstacle2
34.2ReturnPPO-Lag
Evaluation results
| Method | Links | ||
|---|---|---|---|
| PPO-Lag2026.02 | 34.2 | 0 | |
| A2C-GP-Shield2026.02 | 22.9 | 1 | |
| DMPS2026.02 | 20.2 | 1 | |
| CPO2026.02 | 15.3 | 0.939 | |
| MPS2026.02 | -1.82 | 1 |
| Method | Links | ||
|---|---|---|---|
| PPO-Lag2026.02 | 34.2 | 0 | |
| A2C-GP-Shield2026.02 | 22.9 | 1 | |
| DMPS2026.02 | 20.2 | 1 | |
| CPO2026.02 | 15.3 | 0.939 | |
| MPS2026.02 | -1.82 | 1 |