ResearchBenchmarksMulti-Agent Reinforcement Learning on MPE pz-mpe-simple-spreadMulti-Agent Reinforcement Learning on MPE pz-mpe-simple-spreadFollow191.18Number of learnable parameters (K)RIIT101.7816124.9908148.2171.4092Apr 17, 2025Evaluation resultsMethodMethodLinksNumber of learnable parameters (K)Baseline AverageReduction RateRIIT2025.04191.18——Qatten2025.04191.11——QPLEX2025.04154.76——QMIX2025.04140.42——QLLM2025.04105.22166.7436.88