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

Cooperative Multi-Agent Reinforcement Learning on SMAC 8m map

17.8Return

KD-MARL

Updated 9d ago

Evaluation Results

Method	Links
KD-MARL 2026.04		17.8	88.97	17.3
KD-MARL 2026.04		17.6	88.23	15.8
MAPPO 2026.04		17	89.91	21.5
QMIX 2026.04		16	92.19	21.9
VDN 2026.04		15	75.32	19
MAPPO 2026.04		14	77.82	22
QMIX 2026.04		12.5	64.78	18.1
MAPPO 2026.04		10	60.07	21.8
VDN 2026.04		10	52.11	17.2
QMIX 2026.04		8.5	48.13	10.8
VDN 2026.04		6	33.05	15