Multi-agent Reinforcement Learning on SMAC 3s_vs_3z Homog.
97.3Win RateMARIE
Evaluation Results
| Method | Links | |
|---|---|---|
| MARIEMethod Category=Multi-Agent World Model Methods, Execution Protocol=CTDE, Training Steps=100K, Number of Seeds=1002026.02 | 97.3 | |
| MetaMindMethod Category=Multi-Agent World Model Methods, Execution Protocol=Decentralized, Training Steps=100K, Number of Seeds=1002026.02 | 95.1 | |
| DCWMCMethod Category=Multi-Agent World Model Methods, Execution Protocol=Decentralized, Training Steps=100K, Number of Seeds=1002026.02 | 63.4 | |
| MAPPOMethod Category=Multi-Agent RL Methods, Execution Protocol=CTDE, Training Steps=100K, Number of Seeds=1002026.02 | 6.8 | |
| MBVDMethod Category=Multi-Agent RL Methods, Execution Protocol=CTDE, Training Steps=100K, Number of Seeds=1002026.02 | 1 |