TemporallyCorrelatedTaskSchedulingforSequenceLearningXueqingWu1LewenWang2YingceXia2WeiqingLiu2LijunWu2ShufangXie2TaoQin2Tie-YanLiu2Abstractneousmachinetranslation,weneedtobegintranslationbeforeread...
PolicyInformationCapacity:Information-TheoreticMeasureforTaskComplexityinDeepReinforcementLearningHirokiFuruta1TatsuyaMatsushima1TadashiKozuno2YutakaMatsuo1SergeyLevine3OfirNachum3ShixiangShaneGu3A...
LearningTaskInformedAbstractionsXiangFu1GeYang12PulkitAgrawal12TommiJaakkola1AbstractEpisodeReturnNoBackgroundCurrentmodel-basedreinforcementlearningVideoDistractionmethodsstrugglewhenoperatingfrom...
ImprovingPredictorsviaCombinationAcrossDiverseTaskCategoriesKwangInKim1AbstractPredictorcombinationisrelatedtomulti-Tasklearning(MTL)andtransferlearning(TL).However,sincenoaccessPredictorcombinatio...
ImprovingGeneralizationinMeta-learningviaTaskAugmentationHuaxiuYao†1Long-KaiHuang2LinjunZhang3YingWei4LiTian2JamesZou1JunzhouHuang2ZhenhuiLi5AbstractquicklylearninganewTaskwithaslittleasafewexampl...
ChebyshevPolynomialCodes:TaskEntanglement-basedCodingforDistributedMatrixMultiplicationSangwooHong1HeecheolYang2YeongseokYoon1TaehyeonCho1JungwooLee1AbstractagivenTaskmuchslowerthanotherworkers,det...
TaskUnderstandingfromConfusingMulti-TaskDataXinSu12YizhouJiang1ShangqiGuo13FengChen132AbstractTaskAnnotationLabelAnnotationBeyondmachinelearning’ssuccessinthespecificTaskTAasnkno1tationSampleAnnot...
TACO:LearningTaskDecompositionviaTemporalAlignmentforControlKyriacosShiarlis1MarkusWulfmeier2SashaSalter2ShimonWhiteson3IngmarPosner2Abstractplatform,LfDrequiresonlytheabilitytocontroltheagent.Many...
Zero-ShotTaskGeneralizationwithMulti-TaskDeepReinforcementLearningJunhyukOh1SatinderSingh1HonglakLee12PushmeetKohli3AbstractFigure1:Exampleof3Dworldandinstructions.TheagentisTaskedtoexecutelongerse...
UnifyingTaskSpecificationinReinforcementLearningMarthaWhite1Abstractjectives,includingoptions(Suttonetal.,1999),state-baseddiscounting(Sutton,1995;Suttonetal.,2011)andinter-Reinforcementlearningtas...