ResearchBenchmarksMulti-agent Reinforcement Learning on MaMuJoCo OMIGA 3-Hopper (Medium-Expert)Follow3,568Average Episode RewardOMSD-141.2224821.74881,784.722,747.6912May 9, 2025Evaluation ResultsMethodMethodLinksAverage Episode RewardOMSD2025.053,568OMIGA2025.05709ICQ2025.05355.44CQLMA2025.0564.82BCQMA2025.0554.31OMAR2025.051.44