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

Cooperative Multi-Agent Reinforcement Learning on SMAC 3m map

19.8Return

MAPPO

Updated 9d ago

Evaluation Results

Method	Links
MAPPO 2026.04		19.8	98.12	6.5
QMIX 2026.04		19.6	98.77	6.6
KD-MARL 2026.04		18.6	94.78	5.5
MAPPO 2026.04		18.2	92.65	6.2
VDN 2026.04		18	85.42	6
KD-MARL 2026.04		18	90.39	4.1
QMIX 2026.04		16	86.34	5.9
MAPPO 2026.04		15	80.34	6.3
VDN 2026.04		13.5	68.31	5.4
QMIX 2026.04		12.5	70.27	3.8
VDN 2026.04		9	52.12	4.3