WassersteinDistributionalNormalizationForRobustDistributionalCertificationofNoisyLabeledDataSungWooPark1JunseokKwon1AbstractWhilethereareseveralmethodsthatcandealwithnoisy-labeleddata,recentmethods...
LearningOnlineAlgorithmswithDistributionalAdviceIliasDiakonikolas1VasilisKontonis1ChristosTzamos1AliVakilian2NikosZarifis1Abstractversary(Koutsoupias&Papadimitriou,2000).Amorere-centlineofworkstudi...
GMAC:ADistributionalPerspectiveonActor-CriticFrameworkDanielWontaeNam1YounghoonKim1ChanY.Park1Abstract(a)TheobservationinputInthispaper,wedeviseaDistributionalframe-(b)Theevaluatedvaluedistribution...
GeneralisedLipschitzRegularisationEqualsDistributionalRobustnessZacCranko1ZhanShi2XinhuaZhang2RichardNock3SimonKornblith3AbstractInordertomakethisnotionofdistrustconcrete,weintro-Theproblemofadvers...
DORO:DistributionalandOutlierRobustOptimizationRuntianZhai1ChenDan1J.ZicoKolter1PradeepRavikumar1Abstractshiftproblems,suchaslearningforalgorithmicfairness(Dworketal.,2012;Barocas&Selbst,2016)where...
ConditionalDistributionalTreatmentEffectwithKernelConditionalMeanEmbeddingsandU-StatisticRegressionJunhyungPark1UriShalit2BernhardScho¨lkopf1KrikamolMuandet1Abstractontheanalysisoftheaveragetreatm...
StochasticallyDominantDistributionalReinforcementLearningJohnD.Martin1MichalLyskawinski1XiaohuLi1BrendanEnglot1AbstractTheConditionalValueatRisk(CVaRα)isapopularstatisticthatmeasuresuncertaintywit...
ADistributionalFrameworkforDataValuationAmirataGhorbani1MichaelP.Kim1JamesZou1Abstracttrainingdataismostvaluableand,hence,mostdeservingofresourcestowardscollectionandannotation.Assuch,aprin-Shapley...
ADistributionalViewonMulti-ObjectivePolicyOptimizationAbbasAbdolmaleki1SandyH.Huang1LeonardHasenclever1MichaelNeunert1H.FrancisSong1MartinaZambelli1MuriloF.Martins1NicolasHeess1RaiaHadsell1MartinRi...
StatisticsandSamplesinDistributionalReinforcementLearningMarkRowland1RobertDadashi2SaurabhKumar2Re´miMunos1MarcG.Bellemare2WillDabney1AbstractthatDRLalgorithmscanbeviewedascombiningastatisti-cales...
NonlinearDistributionalGradientTemporal-DifferenceLearningChaoQu1ShieMannor2HuanXu34Abstractintermediatesteptogenerategoodcontrolpolicy(Gelly&Silver,2008;Tesauro,1992).ThevaluefunctionisknownWedevi...
GeometricLossesforDistributionalLearningArthurMensch12MathieuBlondel3GabrielPeyre´12Abstractadaptation(Courtyetal.,2017),dictionarylearning(Ro-letetal.,2016)andgenerativemodelstraining(MontavonBui...
DistributionalMultivariatePolicyEvaluationandExplorationwiththeBellmanGANDrorFreirich1TzahiShimkin1RonMeir1AvivTamar2Abstracting(DiRL)approach,wherethevaluedistribution,ratherthantheexpectationarel...
DistributionalReinforcementLearningforEfficientExplorationBorislavMavrin12HengshuaiYao3LinglongKong12KaiwenWu4YaoliangYu4AbstractDeterministicenvironmentInDistributionalreinforcementlearning(RL),th...
ImprovingRegressionPerformancewithDistributionalLossesEhsanImani1MarthaWhite1Abstractorabsoluteerrorforregression—butthoselossesarenotnecessarilydirectlyminimized.Thereisgrowingevidencethatconvert...
ImplicitQuantileNetworksforDistributionalReinforcementLearningWillDabney1GeorgOstrovski1DavidSilver1Re´miMunos1Abstractthis,itassumesreturnsareboundedinaknownrangeandtradesoffmean-preservationatth...
ADistributionalPerspectiveonReinforcementLearningMarcG.Bellemare1WillDabney1Re´miMunos1Abstractmentlearning.Specifically,themainobjectofourstudyistherandomreturnZwhoseexpectationisthevalueQ.ThisIn...