DeeplyAggreVaTeD:DifferentiableImitationLearningforSequentialPredictionWenSun1ArunVenkatraman1GeoffreyJ.Gordon2ByronBoots3J.AndrewBagnell1Abstractoptimizeforalossacquiredonlyaftermanypredictions.Re...
CoordinatedMulti-AgentImitationLearningHoangM.Le1YisongYue1PeterCarr2PatrickLucey3AbstractFigure1.Ourmotivatingexampleoflearningcoordinatingbe-haviorpoliciesforteamsportsfromtrackingdata.RedistheWe...
