Multi-Agent Reinforcement Learning on SMAC 6h_vs_8z (test)
19.4Average ScoreDDN
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DDNFramework=DFAC, Training Length=8M timesteps2021.02 | 19.4 | — | |
| LBIprotocol=offline reinforcement learning2024.10 | 18.97 | — | |
| DMIXFramework=DFAC, Training Length=8M timesteps2021.02 | 17.14 | — | |
| VDNTraining Length=8M timesteps2021.02 | 15.41 | — | |
| DIQLTraining Length=8M timesteps2021.02 | 14.94 | — | |
| QMIXTraining Length=8M timesteps2021.02 | 14.37 | — | |
| IQLTraining Length=8M timesteps2021.02 | 13.78 | — | |
| OMIGAprotocol=offline reinforcement learning2024.10 | 12.74 | — | |
| BCQ-MAprotocol=offline reinforcement learning2024.10 | 11.91 | — | |
| ICQprotocol=offline reinforcement learning2024.10 | 11.55 | — | |
| CQL-MAprotocol=offline reinforcement learning2024.10 | 9.95 | — | |
| OMARprotocol=offline reinforcement learning2024.10 | 9.74 | — | |
| QMIX2020.03 | — | 3 |