RepresentationMatters:OfflinePretrainingforSequentialDecisionMakingMengjiaoYang1OfirNachum1AbstractFigure1.Asummaryoftheadvantagesofrepresentationlearningviacontrastiveself-prediction,acrossavariet...
ReinforcementLearningforCost-AwareMarkovDecisionProcessesWesleyA.Suttle1KaiqingZhang2ZhuoranYang3DavidN.Kraemer1JiLiu4Abstractquentlyusedinpractice.Nevertheless,alternativeobjectiveshaveseenincreas...
LearningBinaryDecisionTreesbyArgminDifferentiationValentinaZantedeschi12MattJ.Kusner2VladNiculae3Abstractquadraticprogram(relaxedfromMIP)Weaddresstheproblemoflearningbinarydeci-siontreesthatpartiti...
LearningandPlanninginAverage-RewardMarkovDecisionProcessesYiWan1AbhishekNaik1RichardS.Sutton12Abstractwithit.Forlearningandcombinedmethods,bothcontrolandpredictionproblemscanbefurthersubdividedinto...
InverseDecisionModeling:LearningInterpretableRepresentationsofBehaviorDanielJarrett1AlihanHüyük1MihaelavanderSchaar12AbstractConsiderthe“lifecycle”ofDecisionanalysis[9]intherealworld.First,norm...
EfficientTrainingofRobustDecisionTreesAgainstAdversarialExamplesDanie¨lVos1SiccoVerwer1Abstractetal.,2019),wecloselymimicthegreedyrecursivesplit-tingstrategythattraditionalDecisiontreesuseandwesco...
ConnectingInterpretabilityandRobustnessinDecisionTreesthroughSeparationMichalMoshkovitz1Yao-YuanYang1KamalikaChaudhuri1Abstractetal.,2019;Ross&Doshi-Velez,2017).Inthiswork,wetakearigorousapproachto...
SafeReinforcementLearninginConstrainedMarkovDecisionProcessesAkifumiWachi1YananSui2Abstractessentialrequirement,theprimaryobjectiveisnonethelesstoobtainrewards(e.g.,scientificgain).Safereinforcemen...
ReinforcementLearningforNon-StationaryMarkovDecisionProcesses:TheBlessingof(More)OptimismWangChiCheung1DavidSimchi-Levi2RuihaoZhu2Abstractimizesitscumulativerewards,whilefacingthefollowingchallenge...
ProvableGuaranteesforDecisionTreeInduction:TheAgnosticSettingGuyBlanc1JaneLange1Li-YangTan1AbstractnowthattheybuildaDecisiontreeTforabinaryclassifierf:Rn→{0,1}inagreedy,top-downfashion:Wegivestren...
Onp-normRobustnessofEnsembleDecisionStumpsandTreesYihanWang1HuanZhang2HonggeChen3DuaneBoning3Cho-JuiHsieh2Abstractetal.,2017;Ilyasetal.,2018;Brendeletal.,2018;Chengetal.,2019a;2020),variousalgorith...
LearningAdversarialMarkovDecisionProcesseswithBanditFeedbackandUnknownTransitionChiJin1TianchengJin2HaipengLuo2SuvritSra3TianchengYu3AbstractThemajorityoftheliteratureinlearningMDPsassumesstationar...
GeneralizedandScalableOptimalSparseDecisionTreesJimmyLin1ChudiZhong2DianeHu2CynthiaRudin2MargoSeltzer1Abstractisthattheytendtoproducesuboptimaltreeswithnowayofknowinghowsuboptimalthesolutionis.This...
DoestheMarkovDecisionProcessFittheData:TestingfortheMarkovPropertyinSequentialDecisionMakingChengchunShi1RunzheWan2RuiSong2WenbinLu2LingLeng3Abstract1.1.ContributionsandadvancesofourtestTheMarkovas...
DecisionTreesforDecision-MakingunderthePredict-then-OptimizeFrameworkAdamN.Elmachtoub1JasonCheukNamLiang2RyanMcNellis13Abstract1.IntroductionWeconsidertheuseofDecisiontreesforManyDecision-makingpro...
ConstrainedMarkovDecisionProcessesviaBackwardValueFunctionsHarshSatija123PhilipAmortila12JoellePineau123Abstractalgorithmshasbeenlimitedtosimulators,wherethelearn-ingalgorithmhastheabilitytoresetth...
Clinician-in-the-LoopDecisionMaking:ReinforcementLearningwithNear-OptimalSet-ValuedPoliciesShengpuTang1AdityaModi1MichaelW.Sjoding23JennaWiens1Abstractrewardsignalsviarewardshaping(Lizotteetal.,201...
TopologicalDataAnalysisofDecisionBoundarieswithApplicationtoModelSelectionKarthikeyanNatesanRamamurthy1KushR.Varshney1KrishnanMody12AbstractofneuralnetworkDecisionboundaries.Persistenthomologyinvol...
RobustDecisionTreesAgainstAdversarialExamplesHonggeChen1HuanZhang2DuaneBoning1Cho-JuiHsieh2Abstracttherobustnessoftree-basedmodelsarequitelimited(Paper-notetal.,2016a).Althoughadversarialexamplesan...
OnlineConvexOptimizationinAdversarialMarkovDecisionProcessesAvivRosenberg1YishayMansour12AbstractWeproposeanovelalgorithmfortheadversarialMDPmodelwherethetransitionfunctionisunknowntotheWeconsidero...