PC-MLP:Model-basedReinforcementLearningwithPolicyCoverGuidedExplorationYudaSong1WenSun2Abstractsuccessrate0.5HandEgg0.4Model-basedReinforcementLearning(RL)isa0.3DeepPC-MPL200000popularlearningparad...
SubmodularCostSubmodularCoverwithanApproximateOracleVictoriaG.Crawford1AlanKuhnle2MyT.Thai1AbstractSubmodularCostSubmodularCover(SCSC)Letf,c:2S→R≥02bemonotonesubmodularfunctionsde-Inthiswork,west...
DisCoveringOptionsforExplorationbyMinimizingCoverTimeYuuJinnai1JeeWonPark1DavidAbel1GeorgeKonidaris1AbstractoptionsguaranteedtoreducetheexpectedCovertimeusingthetransitionfunctioneithergiventoorlea...
Cover:LearningCovariate-SpecificVectorRepresentationswithTensorDecompositionsKevinTian1TengZhang2JamesZou3Abstract1.IntroductionWordembeddingisausefulapproachtocap-Theuseoffactorizationsofco-occurr...