Modeling Others using Oneself in Multi-Agent Reinforcement Learning

ModelingOthersusingOneselfinMulti-AgentReinforcementLearningRobertaRaileanu1EmilyDenton1ArthurSzlam2RobFergus12Abstractofunderstandingwhattheotherplayeristryingtoachieve,anagentshouldaskitself“wha...