ResearchBenchmarksMulti-Agent Reinforcement Learning on SMAC 6h vs 8zFollow95Win RateDG-MAPPO75.44880.52485.690.676Jan 22, 2026Evaluation ResultsMethodMethodLinksWin RateStd DevDG-MAPPODifficulty=Hard+, Sigh...Difficulty=Hard+, Sight Range=92026.01952.7MAT-DecDifficulty=Hard+, Sigh...Difficulty=Hard+, Sight Range=92026.0193.84.7MAPPODifficulty=Hard+, Sigh...Difficulty=Hard+, Sight Range=92026.0188.45.7HAPPODifficulty=Hard+, Sigh...Difficulty=Hard+, Sight Range=92026.0176.23.1