Multi-Agent Reinforcement Learning on SMAC 27m_vs_30m (test)
19.71Test Win RateDDN
Evaluation Results
| Method | Links | |
|---|---|---|
| DDNFramework=DFAC, Training Length=8M timesteps2021.02 | 19.71 | |
| DMIXFramework=DFAC, Training Length=8M timesteps2021.02 | 19.43 | |
| QMIXTraining Length=8M timesteps2021.02 | 19.41 | |
| VDNTraining Length=8M timesteps2021.02 | 18.45 | |
| DIQLTraining Length=8M timesteps2021.02 | 14.45 | |
| IQLTraining Length=8M timesteps2021.02 | 14.01 | |
| QMIX2020.03 | 0.49 |