Multi-agent Reinforcement Learning on SMAC 2s_vs_1sc (Homog.)
96.1Win RateMARIE
Evaluation Results
| Method | Links | |
|---|---|---|
| MARIEMethod Category=Multi-Agent World Model Methods, Execution Protocol=CTDE, Training Steps=100K, Number of Seeds=1002026.02 | 96.1 | |
| MetaMindMethod Category=Multi-Agent World Model Methods, Execution Protocol=Decentralized, Training Steps=100K, Number of Seeds=1002026.02 | 93.2 | |
| MAPPOMethod Category=Multi-Agent RL Methods, Execution Protocol=CTDE, Training Steps=100K, Number of Seeds=1002026.02 | 93.1 | |
| DCWMCMethod Category=Multi-Agent World Model Methods, Execution Protocol=Decentralized, Training Steps=100K, Number of Seeds=1002026.02 | 80.4 | |
| MBVDMethod Category=Multi-Agent RL Methods, Execution Protocol=CTDE, Training Steps=100K, Number of Seeds=1002026.02 | 16.1 |