ResearchBenchmarksMulti-Agent Reinforcement Learning on MAMuJoCo Hopper 3x1 (test)Multi-Agent Reinforcement Learning on MAMuJoCo Hopper 3x1 (test)Follow31.02Average Episodic ReturnMMSA2.856810.168417.4824.7916Feb 13, 2026Evaluation resultsMethodMethodLinksAverage Episodic ReturnMMSA2026.0231.02VDN2026.0224.1QMIX2026.0222.09IQL2026.0217.09SMMAE2026.0212.52QPLEX-CIA2026.0212.18MASER2026.025.86QMIX-CIA2026.023.94