List your company
ResearchFormerly WizWand

Multi-Agent Reinforcement Learning on sce1m (test)

100Win RateMAPPO
87.10490.45293.897.148Jun 29, 2026
Updated 4mo ago

Evaluation results

MethodLinks
MAPPO2026.0610037.406
IQL2026.0610026.666
VDN2026.0699.729.794
QTRAN2026.0699.427.993
HRL-IM/CBS2026.0698.525.697
QMIX2026.0698.525.797
COMA2026.0687.619.137