Multi-Agent Reinforcement Learning on sce1 (train)
99.8Win RateMAPPO
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MAPPO2026.06 | 99.8 | 35.849 | |
| HRL-IM/CBS2026.06 | 99.7 | 47.847 | |
| MAPPO2026.06 | 99 | 20.777 | |
| HRL-IM/CBS2026.06 | 98 | 24.513 | |
| VDN2026.06 | 97 | 23.504 | |
| QTRAN2026.06 | 93.7 | 19.946 | |
| QMIX2026.06 | 93.4 | 21.055 | |
| QMIX2026.06 | 92.5 | 13.765 | |
| IQL2026.06 | 92.3 | 19.104 | |
| VDN2026.06 | 92 | 13.11 | |
| COMA2026.06 | 91.1 | 16.356 | |
| IQL2026.06 | 90.4 | 11.782 | |
| QTRAN2026.06 | 89.5 | 14.389 | |
| COMA2026.06 | 87 | 18.107 |