TaylorExpansionsofDiscountFactorsYunhaoTang1MarkRowland2Re´miMunos3MichalValko3Abstractexample,TcouldbethefirsttimetheMDPgetsintoatermi-Inpracticalreinforcementlearning(RL),thedis-nalstate(e.g.,ar...
DiscountFactorasaRegularizerinReinforcementLearningRonAmit1RonMeir1KamilCiosek2Abstractetal.,2019;Zhaoetal.,2019).Inparticular,generalizationiscriticalforsuccessfullydeployingRLagentsthatwereSpecif...