ValueIterationinContinuousActions,StatesandTimeMichaelLutter12ShieMannor13JanPeters2DieterFox14AnimeshGarg15AbstractValueIterationFittedValueIterationContinuousFittedValueIterationClassicalvalueite...
SampleEfficientReinforcementLearningInContinuousStateSpaces:APerspectiveBeyondLinearityDhruvMalik1AldoPacchiano2VishwakSrinivasan1YuanzhiLi1Abstractsuchabenchmark(Bellemareetal.,2013).Agentstrained...
ModelingHierarchicalStructureswithContinuousRecursiveNeuralNetworksJishnuRayChowdhury1CorneliaCaragea1Abstractsomeofthesestructure-awaremethods(Shenetal.,2019a;Qianetal.,2020)alsoexhibitbettersyste...
Model-basedReinforcementLearningforContinuousControlwithPosteriorSamplingYingFan1YifeiMing1AbstractinRLhasbeenoneofthemainchallenges:theagentisexpectedtobalancebetweenexploringunseenstate-actionBal...
LocallyPersistentExplorationinContinuousControlTaskswithSparseRewardsSusanAmin12MaziarGomrokchi12HosseinAboutalebi34HarshSajita12DoinaPrecup12Abstractcallforacleverexplorationstrategythatexposesthe...
LearningSelf-ModulatingAttentioninContinuousTimeSpacewithApplicationstoSequentialRecommendationChaoChen1HaoyuGeng12NianzuYang12JunchiYan12DaiyueXue3JianpingYu3XiaokangYang12Abstractfadeawayduetomat...
EventOutlierDetectioninContinuousTimeSiqiLiu12MilosHauskrecht1Abstractorabsenceofeventsineventsequencesinreal-time.Outlierdetectionisthebasisofmanycriticalreal-worldapplica-Continuous-timeeventsequ...
DeepCoherentExplorationforContinuousControlYijieZhang1HerkevanHoof2Abstractstrategiesandundirectedstrategies(Thrun,1992;Plappertetal.,2018).Whiledirectedstrategiesaimtoextractuse-Inpolicysearchmeth...
DeepContinuousNetworksNergisTomen1SilviaL.Pintea1JanC.vanGemert1Abstractcalcircuits(Schrimpfetal.,2018),andemployCNNsasmodelsofbiologicalvision(Zhuangetal.,2020a).Specif-CNNsandcomputationalmodelso...
ContinuousCoordinationAsaRealisticScenarioforLifelongLearningHadiNekoei1AkileshBadrinaaraayanan12AaronCourville123SarathChandar143Abstract1.IntroductionCurrentdeepreinforcementlearning(RL)algo-Deep...
TheContinuousCategorical:ANovelSimplex-ValuedExponentialFamilyElliottGordon-Rodriguez1GabrielLoaiza-Ganem2JohnP.Cunningham1Abstractcalrelevanceacrossthenaturalandsocialsciences(seePawlowsky-Glahn&E...
SoftSort:AContinuousRelaxationfortheargsortOperatorSebastianPrillo1JulianMartinEisenschlos2Abstracttion.Becauseofthis,operatorssuchasthesoftmaxareWhilesortingisanimportantprocedureincom-ubiquitousi...
Prediction-GuidedMulti-ObjectiveReinforcementLearningforContinuousRobotControlJieXu1YunshengTian1PingchuanMa1DanielaRus1ShinjiroSueda2WojciechMatusik1AbstractRNf2Manyreal-worldcontrolproblemsinvolv...
KernelInterpolationWithContinuousVolumeSamplingAyoubBelhadji1Re´miBardenet1PierreChainais1Abstractandonthecorrespondingweightsw1,...,wN,suchthattheRKHSnormAfundamentaltaskinkernelmethodsistopickno...
InferringDQNstructureforhigh-dimensionalContinuouscontrolAndreySakryukin1ChedyRa¨ıssi23MohanS.Kankanhalli1Abstract(Yunetal.,2017),NLP(Lietal.,2016)andothers,werepublished.Oneofthemainfocusesofrec...
Gradient-freeOnlineLearninginGameswithDelayedRewardsAmélieHéliou1PanayotisMertikopoulos21ZhengyuanZhou3AbstractSimilarissuesalsoariseinoperationsresearch,onlinemachinelearning,andotherfieldswhere...
EffcientContinuousParetoExplorationinMulti-TaskLearningPingchuanMa1TaoDu1WojciechMatusik1Abstractgiverisetoasetofsolutions,knownastheParetoset,withvaryingpreferencesondifferentobjectives.Tasksinmul...
ContinuousGraphNeuralNetworksLouis-PascalA.C.Xhonneux12MengQu12JianTang134Abstracttion(Gilmeretal.,2017),andnaturallanguageunderstand-ing(MarcheggianiandTitov,2017;Yaoetal.,2019).TheThispaperbuilds...
BayesianOptimisationoverMultipleContinuousandCategoricalInputsBinxinRu∗1AhsanS.Alvi∗1VuNguyen1MichaelA.Osborne1StephenJRoberts1AbstractForexample,withadeepneuralnetwork,wemaywanttoadjustthelearni...
Continuous-TimeBayesianNetworkswithClocksNicolaiEngelmann1DominikLinzner1HeinzKoeppl12Abstractfollowafixedparametrizationthathinderstheirexpressive-ness,oraredefinedindiscretetimeasDynamicBayesianS...