Multi-agent Reinforcement Learning on SMAC MMM (Heterog.)
85.7Win RateMetaMind
Evaluation Results
| Method | Links | |
|---|---|---|
| MetaMindMethod Category=Multi-Agent World Model Methods, Execution Protocol=Decentralized, Training Steps=100K, Number of Seeds=1002026.02 | 85.7 | |
| MARIEMethod Category=Multi-Agent World Model Methods, Execution Protocol=CTDE, Training Steps=100K, Number of Seeds=1002026.02 | 83.2 | |
| DCWMCMethod Category=Multi-Agent World Model Methods, Execution Protocol=Decentralized, Training Steps=100K, Number of Seeds=1002026.02 | 68.1 | |
| MAPPOMethod Category=Multi-Agent RL Methods, Execution Protocol=CTDE, Training Steps=100K, Number of Seeds=1002026.02 | 11.2 | |
| MBVDMethod Category=Multi-Agent RL Methods, Execution Protocol=CTDE, Training Steps=100K, Number of Seeds=1002026.02 | 10.5 |