ResearchBenchmarksMulti-agent Reinforcement Learning on MaMuJoCo OMIGA 2-Ant (Expert)Follow2,191Average Episode RewardOMSD237.4016744.58581,251.771,758.9542May 9, 2025Evaluation ResultsMethodMethodLinksAverage Episode RewardOMSD2025.052,191OMIGA2025.052,055.46ICQ2025.052,050BCQMA2025.051,317.73CQLMA2025.051,042.39OMAR2025.05312.54