CoordinatedExplorationinConcurrentReinforcementLearningMariaDimakopoulou1BenjaminVanRoy1Abstractandrefinesestimatesasdataisgathered.Atthestartofeachepisode,theagentsamplesanMDPfromitscurrentposte-W...
CoordinatedMulti-AgentImitationLearningHoangM.Le1YisongYue1PeterCarr2PatrickLucey3AbstractFigure1.Ourmotivatingexampleoflearningcoordinatingbe-haviorpoliciesforteamsportsfromtrackingdata.RedistheWe...
