List your company
ResearchFormerly WizWand

Cooperative Multi-Agent Reinforcement Learning on Adversary (last 2% of train)

85.04Mean Episodic RewardSACHI
7.466427.605747.74567.8843May 8, 2026
Updated 5mo ago

Evaluation results

MethodLinks
SACHIL=2, d=64, K=12026.0585.04
DGN2026.0583.54
CASEC2026.0581.55
QTRAN2026.0579.79
QPLEX2026.0565.69
FOP2026.0544.68
DCG2026.0540.35
DICG2026.0536.51
IQL2026.0533.46
MAPPO2026.0531.83
IPPO2026.0523.54
VDN2026.0518.69
QMIX2026.0510.45