ResearchBenchmarksMulti-Agent Reinforcement Learning on MPE pz-mpe-simple-tagFollow102.28Params (K)QLLM101.0832109.1616117.24125.3184Apr 17, 2025Evaluation ResultsMethodMethodLinksParams (K)Baseline Average ScorePerformance Reduction RateQLLM2025.04102.28125.9118.78QMIX2025.04112.81——QPLEX2025.04128.01——Qatten2025.04129.03——RIIT2025.04132.2——