Multi-Agent Reinforcement Learning on SMAC 5m_vs_6m (test)
18.96Test ReturnLBI
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LBIprotocol=offline reinforcement learning2024.10 | 18.96 | — | |
| OMIGAprotocol=offline reinforcement learning2024.10 | 10.38 | — | |
| CQL-MAprotocol=offline reinforcement learning2024.10 | 10.15 | — | |
| ICQprotocol=offline reinforcement learning2024.10 | 9.47 | — | |
| BCQ-MAprotocol=offline reinforcement learning2024.10 | 9.13 | — | |
| OMARprotocol=offline reinforcement learning2024.10 | 8.76 | — | |
| COMA2020.03 | — | 1 | |
| IQL2020.03 | — | 49 | |
| QMIX2020.03 | — | 70 | |
| VDN2020.03 | — | 70 |