Multi-agent Reinforcement Learning on SMAC corridor Homog.
76.8Win RateMetaMind
Evaluation Results
| Method | Links | |
|---|---|---|
| MetaMindMethod Category=Multi-Agent World Model Methods, Execution Protocol=Decentralized, Training Steps=400K, Number of Seeds=1002026.02 | 76.8 | |
| MARIEMethod Category=Multi-Agent World Model Methods, Execution Protocol=CTDE, Training Steps=400K, Number of Seeds=1002026.02 | 72.5 | |
| DCWMCMethod Category=Multi-Agent World Model Methods, Execution Protocol=Decentralized, Training Steps=400K, Number of Seeds=1002026.02 | 41.2 | |
| MAPPOMethod Category=Multi-Agent RL Methods, Execution Protocol=CTDE, Training Steps=400K, Number of Seeds=1002026.02 | 0 | |
| MBVDMethod Category=Multi-Agent RL Methods, Execution Protocol=CTDE, Training Steps=400K, Number of Seeds=1002026.02 | 0 |