StateEntropyMaximizationwithRandomEncodersforEfficientExplorationYounggyoSeo1LiliChen2JinwooShin1HonglakLee34PieterAbbeel2KiminLee2Abstractproachesencourageagentstovisitdiversestates,butleaveunansw...
SolvingInverseProblemswithaFlow-basedNoiseModelJayWhang1QiLei2AlexandrosG.Dimakis3Abstractplausiblesolutionamongthem.SparsityhasclassicallybeenaveryinfluentialstructuralpriorforvariousinverseWestud...
SolvingChallengingDexterousManipulationTaskswithTrajectoryOptimisationandReinforcementLearningHenryCharlesworth1GiovanniMontana1Abstractthehumanhand—capableoftasksrangingfromcomplexgraspingtowriti...
SMG:AShufflingGradient-BasedMethodwithMomentumTrangH.Tran1LamM.Nguyen2QuocTran-Dinh3Abstractlearning,including,butnotlimitedto,logisticregression,multi-kernellearning,conditionalrandomfields,andneu...
SinIR:EffcientGeneralImageManipulationwithSingleImageReconstructionJihyeongYoo1QifengChen1Abstractdeeplearningbecamepopular,provinginternalapproachescanbesuccessfullyappliedtoseveralimagemanipulati...
SimpleandEffectiveVAETrainingwithCalibratedDecodersOlehRybkin1KostasDaniilidis1SergeyLevine2AbstractHowever,inpractice,manyoftheseapproachesrequirecarefulmanualtuningofthebalancebetweentwotermsthat...
SiameseXML:SiameseNetworksmeetExtremeClassifierswith100MLabelsKunalDahiya1AnanyeAgarwal1DeepakSaini2GururajK3JianJiao3AmitSingh3SumeetAgarwal1PurushottamKar42ManikVarma21Abstractdescriptionse.g.,pr...
Self-supervisedGraph-levelRepresentationLearningwithLocalandGlobalStructureMinghaoXu1HangWang1BingbingNi1HongyuGuo2JianTang345Abstract2020).Thesemethodsareusuallytrainedinasupervisedfashion,whichre...
ScalingMulti-AgentReinforcementLearningwithSelectiveParameterSharingFilipposChristianos1GeorgiosPapoudakis1ArrasyRahman1StefanoV.Albrecht1Abstract(e.g.(Guptaetal.,2017))wherebyagentssharesomeorallp...
ScalableEvaluationofMulti-AgentReinforcementLearningwithMeltingPotJoelZ.Leibo1EdgarDue´n˜ez-Guzma´n1AlexanderSashaVezhnevets1JohnP.Agapiou1PeterSunehag1RaphaelKoster1JaydMatyas1CharlesBeattie1Ig...
Sample-OptimalPACLearningofHalfspaceswithMaliciousNoiseJieShen1AbstractGenerallyspeaking,alargebodyofexistingworksstudytheproblemoflearninghalfspacesunderlabelnoise.Thisin-WestudyefficientPAClearni...
SafeReinforcementLearningwithLinearFunctionApproximationSanaeAmani1ChristosThrampoulidis2LinF.Yang1Abstractactionmayleadtocatastrophicresults.Thus,safetyinRLhasbecomeaseriousissuethatrestrictstheap...
RobustPureExplorationinLinearBanditswithLimitedBudgetAyyaAlieva1AshokCutkosky2AbhimanyuDas3Abstracttheexplorationphaseshouldbesomehowefficient-wewishtomakethebestuseofourlimitedbudgetinordertoWecon...
RNNwithParticleFlowforProbabilisticSpatio-temporalForecastingSoumyasundarPal†1LihengMa†1YingxueZhang2MarkCoates1Abstract2016;Kipf&Welling,2017).Recentworksestablishthatgraph-basedspatio-temporalm...
Risk-SensitiveReinforcementLearningwithFunctionApproximation:ADebiasingApproachYingjieFei1ZhuoranYang2ZhaoranWang1Abstractrisk-seekingobjectiveandβ<0inducesarisk-averseone.ItcanalsobeseenthatVβte...
RevisitingPointCloudShapeClassificationwithaSimpleandEffectiveBaselineAnkitGoyal1HeiLaw1BoweiLiu1AlejandroNewell1JiaDeng1AbstractFigure1.PerformanceofdifferentmodelsonModelNet40.Thoseusing>1024poin...
RethinkingRotatedObjectDetectionwithGaussianWassersteinDistanceLossXueYang123JunchiYan12QiMing4WentaoWang1XiaopengZhang3QiTian3AbstractFigure1.ComparisonofthedetectionresultsbetweenSmoothL1loss-bas...
RelativePositionalEncodingforTransformerswithLinearComplexityAntoineLiutkus1OndrˇejC´ıfka2Shih-LunWu345UmutS¸ims¸ekli6Yi-HsuanYang35Gae¨lRichard2AbstractFigure1.Examplesofattentionpatternsobs...
ReinforcementLearningwithPrototypicalRepresentationsDenisYarats12RobFergus1AlessandroLazaric2LerrelPinto1Abstractfromrewardsaloneissampleinefficientandleadstopoorperformance.Priorwork(Srinivasetal....
RegularizingtowardsCausalInvariance:LinearModelswithProxiesMichaelOberst1NikolajThams2JonasPeters2DavidSontag1AbstractβxAβyWeproposeamethodforlearninglinearmod-XαYelswhosepredictiveperformanceis...