StabilizingEquilibriumModelsbyJacobianRegularizationShaojieBai1VladlenKoltun2J.ZicoKolter1AbstractEquilibriumzbytheimplicitfunctiontheorem(Krantz&Parks,2012),irrespectiveofthemethodusedtosolveforDe...
Multi-AgentTrainingbeyondZero-SumwithCorrelatedEquilibriumMeta-SolversLukeMarris12PaulMuller13MarcLanctot1KarlTuyls1ThoreGraepel12AbstractAvisetal.,2010;Harsanyi&Selten,1988).2Two-player,constant-s...
SparsifiedLinearProgrammingforZero-SumEquilibriumFindingBrianHuZhang1TuomasSandholm1234Abstractgramming(LP)canbeusedtosolve—thatis,tofindaNashEquilibriumin—imperfect-informationtwo-playerzero-sum...
ChannelEquilibriumNetworksforLearningDeepRepresentationWenqiShao1ShitaoTang2XingangPan3PingTan2XiaogangWang1PingLuo4Abstractareimportantcomponentsforawiderangeoftaskssuchasimageclassification(Ioffe...
IdentifytheNashEquilibriuminStaticGameswithRandomPayoffsYichiZhou1JialianLi1JunZhu1Abstracttoestimatethepracticalgamesthroughsimulation.Intheempiricalmodeling,pure-strategyprofilesofplayersareWestu...
GeneralizationandEquilibriuminGenerativeAdversarialNets(GANs)SanjeevArora1RongGe2YingyuLiang1TengyuMa1YiZhang1AbstractFigure1.ProbabilitydensityDrealwithmanypeaksandvalleysItisshownthattrainingofge...