ResearchBenchmarksMulti-agent Reinforcement Learning on MaMuJoCo (OMIGA) 3-Hopper (Expert)Follow3,595Average Episode RewardOMSD-141.3456828.66721,798.682,768.6928May 9, 2025Evaluation ResultsMethodMethodLinksAverage Episode RewardOMSD2025.053,595OMIGA2025.05859.63ICQ2025.05754.74CQLMA2025.05159.14BCQMA2025.0577.85OMAR2025.052.36