Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning

StabilisingExperienceReplayforDeepMulti-AgentReinforcementLearningJakobFoerster1NantasNardelli1GregoryFarquhar1TriantafyllosAfouras1Philip.H.S.Torr1PushmeetKohli2ShimonWhiteson1Abstractmulti-agents...