Multi-Agent Reinforcement Learning on MPE Simple Spread
-46ReturnMAPPO
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MAPPOObservation Setting=FO2026.04 | -46 | 8.1 | |
| KD-MARLObservation Setting=LH2026.04 | -48.5 | 4.2 | |
| KD-MARLObservation Setting=LH+A2026.04 | -50.5 | 4.1 | |
| QMIXObservation Setting=FO2026.04 | -55 | 4.9 | |
| MAPPOObservation Setting=LH2026.04 | -84 | 7.3 | |
| VDNObservation Setting=FO2026.04 | -92 | 5.1 | |
| MAPPOObservation Setting=LH+A2026.04 | -120 | 4.5 | |
| QMIXObservation Setting=LH2026.04 | -142 | 4.6 | |
| VDNObservation Setting=LH2026.04 | -185 | 5 | |
| QMIXObservation Setting=LH+A2026.04 | -210 | 4.3 | |
| VDNObservation Setting=LH+A2026.04 | -248 | 4.7 |