TaylorExpansionsofDiscountFactorsYunhaoTang1MarkRowland2Re´miMunos3MichalValko3Abstractexample,TcouldbethefirsttimetheMDPgetsintoatermi-Inpracticalreinforcementlearning(RL),thedis-nalstate(e.g.,ar...
FindingRelevantInformationviaaDiscreteFourierExpansionMohsenHeidari1JithinK.Sreedharan2GilI.Shamir3WojciechSzpankowski1Abstractcapturenon-linearrelations(Grettonetal.,2005;Chenetal.,2017;Weietal.,2...
TaylorExpansionPolicyOptimizationYunhaoTang1MichalValko2Re´miMunos2Abstractgorithmicideashavecontributedsignificantlytostabilizingpolicyoptimization.Inthiswork,weinvestigatetheapplicationofTaylore...