Multi-AgentTrainingbeyondZero-SumwithCorrelatedEquilibriumMeta-SolversLukeMarris12PaulMuller13MarcLanctot1KarlTuyls1ThoreGraepel12AbstractAvisetal.,2010;Harsanyi&Selten,1988).2Two-player,constant-s...
Infinite-DimensionalOptimizationforZero-SumGamesviaVariationalTransportLewisLiu1YufengZhang2ZhuoranYang3RezaBabanezhad4ZhaoranWang2Abstract(NNs)),whichisofindependentinterest.Gameoptimizationhasbee...
DecentralizedSingle-TimescaleActorCriticonZero-SumTwo-PlayerStochasticGamesHongyiGuo1ZuyueFu1ZhuoranYang2ZhaoranWang1AbstractasMarkovdecisionprocess(Puterman,2014,MDP),whereanagentaimstolearnanopti...
SparsifiedLinearProgrammingforZero-SumEquilibriumFindingBrianHuZhang1TuomasSandholm1234Abstractgramming(LP)canbeusedtosolve—thatis,tofindaNashequilibriumin—imperfect-informationtwo-playerZero-Sum...
ConvergingtoTeam-MaxminEquilibriainZero-SumMultiplayerGamesYouzhiZhang1BoAn1Abstract(NEs)forZero-Sumgames(Nash,1951)vialinearprograms(VonNeumann&Morgenstern,1953;VonStengel,1996;Efficientlycomputin...
Open-endedLearninginSymmetricZero-SumGamesDavidBalduzzi1MartaGarnelo1YoramBachrach1WojciechM.Czarnecki1JulienPerolat1MaxJaderberg1ThoreGraepel1Abstractofwhattesttotake,orwhatobjectivetooptimize,isn...
RegretMinimizationinBehaviorally-ConstrainedZero-SumGamesGabrieleFarina1ChristianKroer1TuomasSandholm1Abstractset,andinstantiatingastandardregretminimizerateachinformationsetinordertominimizelocalr...