ResearchBenchmarksMulti-Agent Reinforcement Learning on MAMuJoCo Ant 8x1 (test)Follow45.06Average Episodic ReturnMMSA-3.9768.754521.48534.2155Feb 13, 2026Evaluation ResultsMethodMethodLinksAverage Episodic ReturnMMSA2026.0245.06QMIX2026.0233.5VDN2026.0226.73SMMAE2026.0222.62IQL2026.0222.5QMIX-CIA2026.0222.23MASER2026.0213.65QPLEX-CIA2026.02-2.09