Cooperative Multi-Agent Reinforcement Learning on SMAC 3s5z map
18.7ReturnQMIX
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| QMIXConfiguration=FO2026.04 | 18.7 | 60.48 | 12 | |
| MAPPOConfiguration=FO2026.04 | 18.5 | 68.31 | 11.5 | |
| KD-MARLConfiguration=LH2026.04 | 17.2 | 60.28 | 9.7 | |
| MAPPOConfiguration=LH2026.04 | 16.8 | 55.66 | 13.5 | |
| VDNConfiguration=FO2026.04 | 16.5 | 53.42 | 10.8 | |
| KD-MARLConfiguration=LH+A2026.04 | 16.5 | 58.17 | 7.9 | |
| QMIXConfiguration=LH2026.04 | 15 | 50.12 | 10.2 | |
| MAPPOConfiguration=LH+A2026.04 | 13.5 | 42.54 | 12.2 | |
| VDNConfiguration=LH2026.04 | 11 | 40.33 | 9.8 | |
| QMIXConfiguration=LH+A2026.04 | 10.5 | 36.95 | 6 | |
| VDNConfiguration=LH+A2026.04 | 7 | 24.12 | 8 |