BootstrappingFittedQ-EvaluationforOff-PolicyInferenceBotaoHao1XiangJi2YaqiDuan2HaoLu2CsabaSzepesva´ri13MengdiWang12Abstractetal.,2013;Munos&Szepesva´ri,2008;Leetal.,2019).Inpractice,FQEhasdemonst...
BoostedFittedQ-IterationSamueleTosatto12MatteoPirotta3CarloD’Eramo1MarcelloRestelli1Abstractisobtainedbysolvingasequenceofsupervisedlearningproblemswhere,ateachiteration,theapplicationoftheThispap...
