Cooperative Multi-Agent Reinforcement Learning on SMAC 3m map
19.8ReturnMAPPO
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MAPPOConfiguration=FO2026.04 | 19.8 | 98.12 | 6.5 | |
| QMIXConfiguration=FO2026.04 | 19.6 | 98.77 | 6.6 | |
| KD-MARLConfiguration=LH2026.04 | 18.6 | 94.78 | 5.5 | |
| MAPPOConfiguration=LH2026.04 | 18.2 | 92.65 | 6.2 | |
| VDNConfiguration=FO2026.04 | 18 | 85.42 | 6 | |
| KD-MARLConfiguration=LH+A2026.04 | 18 | 90.39 | 4.1 | |
| QMIXConfiguration=LH2026.04 | 16 | 86.34 | 5.9 | |
| MAPPOConfiguration=LH+A2026.04 | 15 | 80.34 | 6.3 | |
| VDNConfiguration=LH2026.04 | 13.5 | 68.31 | 5.4 | |
| QMIXConfiguration=LH+A2026.04 | 12.5 | 70.27 | 3.8 | |
| VDNConfiguration=LH+A2026.04 | 9 | 52.12 | 4.3 |