ResearchBenchmarksOffline Multi-Agent Reinforcement Learning on MPE World (Medium)Offline Multi-Agent Reinforcement Learning on MPE World (Medium)Follow104.9Average Normalized ScorePLCQL65.976.02586.1596.275Mar 30, 2026Evaluation resultsMethodMethodLinksAverage Normalized ScorePLCQL2026.03104.9SPaCQL2026.0398.1CFCQL2026.0393.8DoF2026.0385.2OMAR2026.0374.6MA-TD3+BC2026.0373.4IQL2026.0370.5MACQL2026.0367.4