ResearchBenchmarksMulti-Agent Reinforcement Learning on MAMuJoCo HalfCheetah 6x1 (test)Follow43.1Average Episodic ReturnMMSA-11.35442.782816.9231.0572Feb 13, 2026Evaluation ResultsMethodMethodLinksAverage Episodic ReturnMMSA2026.0243.1QMIX2026.0235.83VDN2026.0220.13IQL2026.0216.03QMIX-CIA2026.02-2.18MASER2026.02-3.14SMMAE2026.02-3.28QPLEX-CIA2026.02-9.26