Reinforcement Learning on obstacle3 non-convex
33.4ReturnPPO-Lag
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PPO-Lag2026.02 | 33.4 | 14.8 | |
| CPO2026.02 | 8.56 | 90 | |
| A2C-GP-Shield2026.02 | 4.69 | 100 | |
| DMPS2026.02 | 4.28 | 100 | |
| MPS2026.02 | -0.67 | 100 |
Loading the SOTA2 catalog…
| Method | Links | ||
|---|---|---|---|
| PPO-Lag2026.02 | 33.4 | 14.8 | |
| CPO2026.02 | 8.56 | 90 | |
| A2C-GP-Shield2026.02 | 4.69 | 100 | |
| DMPS2026.02 | 4.28 | 100 | |
| MPS2026.02 | -0.67 | 100 |