Multi-agent Reinforcement Learning on SMAC 2m_vs_1z (Homog.)
93.1Win RateMARIE
Evaluation Results
| Method | Links | |
|---|---|---|
| MARIEMethod Category=Multi-Agent World Model Methods, Execution Protocol=CTDE, Training Steps=100K, Number of Seeds=1002026.02 | 93.1 | |
| MetaMindMethod Category=Multi-Agent World Model Methods, Execution Protocol=Decentralized, Training Steps=100K, Number of Seeds=1002026.02 | 91.7 | |
| MAPPOMethod Category=Multi-Agent RL Methods, Execution Protocol=CTDE, Training Steps=100K, Number of Seeds=1002026.02 | 84.6 | |
| DCWMCMethod Category=Multi-Agent World Model Methods, Execution Protocol=Decentralized, Training Steps=100K, Number of Seeds=1002026.02 | 75.1 | |
| MBVDMethod Category=Multi-Agent RL Methods, Execution Protocol=CTDE, Training Steps=100K, Number of Seeds=1002026.02 | 38.2 |