LearningtoWeightImperfectDemonstrationsYunkeWang1ChangXu2BoDu1HonglakLee34Abstractanyaccesstorewardsignal,hasachievedgreatsuccessinmanysequentialdecisionmakingproblems(Stadieetal.,Thispaperinvestig...
FromPoincare´RecurrencetoConvergenceinImperfectInformationGames:FindingEquilibriumviaRegularizationJulienPerolat1RemiMunos1Jean-BaptisteLespiau1ShayeganOmidshafiei1MarkRowland1PedroOrtega1NeilBurc...
OnlineLearningwithImperfectHintsAdityaBhaskara1AshokCutkosky23RaviKumar2ManishPurohit2Abstracthencedesirable.Theframeworkofonlineconvexoptimiza-tionisquitepowerful,general,andhasbeenextensivelyWeco...
FastComputationofNashEquilibriainImperfectInformationGamesRemiMunos1JulienPerolat1Jean-BaptisteLespiau1MarkRowland1BartDeVylder1MarcLanctot1FinbarrTimbers1DanielHennes1ShayeganOmidshafiei1AudrunasG...
ImitationLearningfromImperfectDemonstrationYueh-HuaWu12NontawatCharoenphakdee32HanBao32VootTangkaratt2MasashiSugiyama23Abstractmaximumentropy(Ziebartetal.,2008).Imitationlearning(IL)aimstolearnanop...