ResearchBenchmarksMulti-Agent Reinforcement Learning on Level-Based Foraging 2s-8x8-2p-2f-coop v2 (test)Follow93Final Episode ReturnMMSA-1.6422.9347.572.07Feb 13, 2026Evaluation ResultsMethodMethodLinksFinal Episode ReturnMMSA2026.0293MAA2C2026.0277IPPO2026.0276QMIX2026.0273VDN2026.0271MAPPO2026.0269IQL2026.0265MADDPG2026.0254COMA2026.026SMMAE2026.022