ResearchBenchmarksMulti-Agent Reinforcement Learning on SMAC 2m1zFollow0.038State EntropySIPO-RBF0.02760.03030.0330.0357Oct 23, 2023Evaluation ResultsMethodMethodLinksState EntropyWin RateSIPO-RBF2023.100.038100SIPO-RBFk=12k=122023.100.038—SIPO-WD2023.100.036100SIPO-WDk=12k=122023.100.036—DIPG2023.100.032100RSPO2023.100.032100RSPOk=12k=122023.100.032—DIPGk=12k=122023.100.032—DvD2023.100.03100DvDk=12k=122023.100.03—SMERL2023.100.028100SMERLk=12k=122023.100.028—PPO2023.10—100