ResearchBenchmarksMulti-Agent Reinforcement Learning on Level-Based Foraging 10x10-4p-3f v2 (test)Follow88Final Episode ReturnMMSA0.6423.324668.68Feb 13, 2026Evaluation ResultsMethodMethodLinksFinal Episode ReturnMMSA2026.0288MAA2C2026.0260IPPO2026.0258VDN2026.0257IQL2026.0237QMIX2026.0231MAPPO2026.0227SMMAE2026.0212MADDPG2026.028COMA2026.024