Share your thoughts, 1 month free Claude Pro on usSee more

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

-17.22Mean Episodic Reward

SACHI

Updated 22d ago

Evaluation Results

Method	Links
SACHI 2026.05		-17.22
DGN 2026.05		-17.82
QMIX 2026.05		-18.45
MAPPO 2026.05		-19.44
IPPO 2026.05		-20.38
DCG 2026.05		-21.19
DICG 2026.05		-22.45
VDN 2026.05		-25.68
IQL 2026.05		-27.7
QPLEX 2026.05		-29.49
QTRAN 2026.05		-34.29
CASEC 2026.05		-43.79
FOP 2026.05		-48.15