ResearchBenchmarksOffline Multi-Agent Reinforcement Learning on MaMuJoCo Half-C (Medium-Replay)Follow73.1Average Normalized ScorePLCQL25.2637.6850.162.52Mar 30, 2026Evaluation ResultsMethodMethodLinksAverage Normalized ScorePLCQL2026.0373.1SPaCQL2026.0366.1CFCQL2026.0359.5IQL2026.0358.8OMAR2026.0357.7MACQL2026.0337MA-TD3+BC2026.0327.1