Cooperative Multi-Agent Reinforcement Learning on SMAC 5m_vs_6m map
19.1ReturnQMIX
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| QMIXConfiguration=FO2026.04 | 19.1 | 58.93 | 12.3 | |
| MAPPOConfiguration=FO2026.04 | 18 | 61.85 | 12 | |
| KD-MARLConfiguration=LH2026.04 | 16.8 | 58.66 | 10 | |
| MAPPOConfiguration=LH2026.04 | 16.5 | 58.09 | 14 | |
| KD-MARLConfiguration=LH+A2026.04 | 16.5 | 56.15 | 8 | |
| VDNConfiguration=FO2026.04 | 16 | 50.1 | 11 | |
| QMIXConfiguration=LH2026.04 | 14 | 50.12 | 10.5 | |
| MAPPOConfiguration=LH+A2026.04 | 13 | 44.78 | 12.7 | |
| VDNConfiguration=LH2026.04 | 11 | 38.22 | 10.2 | |
| QMIXConfiguration=LH+A2026.04 | 10 | 38.79 | 6.2 | |
| VDNConfiguration=LH+A2026.04 | 7 | 25.14 | 8.2 |