Multi-Agent Reinforcement Learning on MPE Adversary
19.1ReturnQMIX
Evaluation results
| Method | Links | ||
|---|---|---|---|
| QMIXObservation Setting=FO2026.04 | 19.1 | 7.1 | |
| MAPPOObservation Setting=FO2026.04 | 18 | 10.5 | |
| KD-MARLObservation Setting=LH2026.04 | 16.8 | 6.3 | |
| MAPPOObservation Setting=LH2026.04 | 16.5 | 9.4 | |
| KD-MARLObservation Setting=LH+A2026.04 | 16.5 | 5.9 | |
| VDNObservation Setting=FO2026.04 | 16 | 6.2 | |
| QMIXObservation Setting=LH2026.04 | 14 | 6.9 | |
| MAPPOObservation Setting=LH+A2026.04 | 13 | 6.2 | |
| VDNObservation Setting=LH2026.04 | 11 | 6 | |
| QMIXObservation Setting=LH+A2026.04 | 10 | 6.2 | |
| VDNObservation Setting=LH+A2026.04 | 7 | 5.8 |