ResearchBenchmarksMulti-Agent Reinforcement Learning on MPE pz-mpe-simple-adversaryFollow124.36Params (K)RIIT100.4608106.6654112.87119.0746Apr 17, 2025Evaluation ResultsMethodMethodLinksParams (K)Baseline AverageReduction RateRIIT2025.04124.36——QPLEX2025.04122.76——Qatten2025.04118.28——QMIX2025.04107.27——QLLM2025.04101.38118.5814.52