OptionsasREsponses:GroundingBehaviouralHierarchiesinMulti-AgentReinforcementLearningAlexanderSashaVezhnevets1YuhuaiTonyWu12MariaEckstein31Re´miLeblond1JoelZ.Leibo1Abstractproblemofbuildingagentswi...
FindingOptionsthatMinimizePlanningTimeYuuJinnai1DavidAbel1DEllisHershkowitz2MichaelL.Littman1GeorgeKonidaris1AbstractBarto,2009;Bacon,2013;Moradietal.,2012),findingre-peatedpolicyfragments(Pickett&...
DiscoveringOptionsforExplorationbyMinimizingCoverTimeYuuJinnai1JeeWonPark1DavidAbel1GeorgeKonidaris1AbstractOptionsguaranteedtoreducetheexpectedcovertimeusingthetransitionfunctioneithergiventoorlea...