FindingtheStochasticShortestPathwithLowRegret:TheAdversarialCostandUnknownTransitionCaseLiyuChen1HaipengLuo1Abstractendwithinafixednumberofstepsisextensivelystudiedinrecentyears(oftenknownasepisodi...
Near-optimalRegretBoundsforStochasticShortestPathAlonCohen1HaimKaplan12YishayMansour12AvivRosenberg2AbstractThefocusofthisworkisonregretminimizationinSSP.Itbuildsonextensiveliteratureontheoreticala...