ResearchBenchmarksMulti-Agent Reinforcement Learning on SMAC terran_10_vs_11 v2Follow13.98Mean ReturnACPPO10.433611.354312.27513.1957Jun 29, 2026Evaluation ResultsMethodMethodLinksMean ReturnStandard ErrorACPPONumber of seeds=5, Bac...Number of seeds=5, Backbone=PPO2026.0613.981.43QMIXNumber of seeds=5, Bac...Number of seeds=5, Backbone=PPO2026.0613.50.73MAPPONumber of seeds=5, Bac...Number of seeds=5, Backbone=PPO2026.0612.030.5VDNNumber of seeds=5, Bac...Number of seeds=5, Backbone=PPO2026.0611.590.67HAPPONumber of seeds=5, Bac...Number of seeds=5, Backbone=PPO2026.0610.570.58