QMIX Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

QMIX:MonotonicValueFunctionFactorisationforDeepMulti-AgentReinforcementLearningTabishRashid1MikayelSamvelyan2ChristianSchroederdeWitt1GregoryFarquhar1JakobFoerster1ShimonWhiteson1Abstract(a)5Marine...