ResearchBenchmarksMulti-Agent Reinforcement Learning on Level-Based Foraging 2s-10x10-3p-3fMulti-Agent Reinforcement Learning on Level-Based Foraging 2s-10x10-3p-3fFollow102.66Parameters (K)QLLM101.65108.4675115.285122.1025Apr 17, 2025Evaluation resultsMethodMethodLinksParameters (K)Baseline Average ScoreReduction RateQLLM2025.04102.66121.1915.28QMIX2025.04109.74——Qatten2025.04120.04——QPLEX2025.04125.45——RIIT2025.04127.91——