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

Multi-Agent Reinforcement Learning on MPE Simple Spread

-46Return

MAPPO

Updated 9d ago

Evaluation Results

Method	Links
MAPPO 2026.04		-46	8.1
KD-MARL 2026.04		-48.5	4.2
KD-MARL 2026.04		-50.5	4.1
QMIX 2026.04		-55	4.9
MAPPO 2026.04		-84	7.3
VDN 2026.04		-92	5.1
MAPPO 2026.04		-120	4.5
QMIX 2026.04		-142	4.6
VDN 2026.04		-185	5
QMIX 2026.04		-210	4.3
VDN 2026.04		-248	4.7