BoostingforControlofDynamicalSystemsNamanAgarwal1NatalyBrukhim21EladHazan21ZhouLu2Abstractofthesystem,andhenceitisoftennota-prioriclearhowtoobtainameaningfulguaranteewhenswitchingbetweenorWestudyth...
OnlineControlwithAdversarialDisturbancesNamanAgarwal1BrianBullins21EladHazan21ShamM.Kakade341KaranSingh21AbstractChallenge1.Perhapsthemostimportantchallengeweaddressisindealingwitharbitrarydisturba...
IterativeLinearizedControl:StableAlgorithmsandComplexityGuaranteesVincentRoulet1SiddharthaSrinivasa2DmitriyDrusvyatskiy3ZaidHarchaoui1AbstractWehighlighttheequivalenceofdynamicprogrammingandgradien...
Grid-WiseControlforMulti-AgentReinforcementLearninginVideoGameAILeiHan1PengSun1YaliDu23JiechaoXiong1QingWang1XinghaiSun1HanLiu4TongZhang5Abstractetal.,2016),etc.Amongthese,RLingameAIresearchattract...
ControlRegularizationforReducedVarianceReinforcementLearningRichardCheng1AbhinavVerma2Ga´borOrosz3SwaratChaudhuri2YisongYue1JoelW.Burdick1Abstractrithmsfocusonmaximizingthelong-termrewardthroughtr...
StyleTokens:UnsupervisedStyleModeling,ControlandTransferinEnd-to-EndSpeechSynthesisYuxuanWang1DaisyStanton1YuZhang1RJSkerry-Ryan1EricBattenberg1JoelShor1YingXiao1FeiRen1YeJia1RifA.Saurous1Abstracto...
StructuredControlNetsforDeepReinforcementLearningMarioSrouji1JianZhang2RuslanSalakhutdinov12AbstractInrecentyears,DeepReinforcementLearningFigure1.TheproposedStructuredControlNet(SCN)forpolicyhasma...
SAFFRON:anAdaptiveAlgorithmforOnlineControloftheFalseDiscoveryRateAadityaRamdas1TijanaZrnic2MartinJ.Wainwright1MichaelI.Jordan1Abstract1.IntroductionIntheonlinefalsediscoveryrate(FDR)problem,Itisno...
Non-LinearMotorControlbyLocalLearninginSpikingNeuralNetworksAdityaGilra12WulframGerstner1AbstractDadarlatetal.,2015).Forwardmodelsuseneuralmotorcommandstopredictbodymovement,whileinversemod-Learnin...
LearningEquationsforExtrapolationandControlSubhamS.Sahoo1ChristophH.Lampert2GeorgMartius3AbstractMachinelearningresearchhasonlyveryrecentlystartedtolookintorelatedtechniques.Asafirstwork,Martius&We...
AnOptimalControlApproachtoDeepLearningandApplicationstoDiscrete-WeightNeuralNetworksQianxiaoLi1ShujiHao1Abstractversionsoftheabovealgorithms.Morebroadly,necessaryconditionsforoptimalitycanbederived...
UncertaintyAssessmentandFalseDiscoveryRateControlinHigh-DimensionalGrangerCausalInferenceAdityaChaudhry1PanXu2QuanquanGu2AbstractInstatistics,causalityisoftenestablishedbymeansofacon-trolled,random...
PredictionandControlwithTemporalSegmentModelsNikhilMishra1PieterAbbeel12IgorMordatch2Abstracttasksinthesameenvironment.Additionally,learningdif-ferentiabledynamicsmodels(suchasthosebasedonneuralWei...
NeuralEpisodicControlAlexanderPritzel1BenignoUria1SriramSrinivasan1Adria`Puigdome`nechBadia1OriolVinyals1DemisHassabis1DaanWierstra1CharlesBlundell1Abstractlearningratesmeanthatexperiencecanonlybei...
ImprovingStochasticPolicyGradientsinContinuousControlwithDeepReinforcementLearningusingtheBetaDistributionPo-WeiChou1DanielMaturana1SebastianScherer1AbstractFigure1.AnexampleofcontinuousControlwith...