DifferentiableParticleFilteringviaEntropy-RegularizedOptimalTransportAdrienCorenflos1JamesThornton2GeorgeDeligiannidis2ArnaudDoucet2Abstractprocess(Xt)t≥1andY-valuedobservations(Yt)t≥1satis-fying...
AcceleratedMessagePassingforEntropy-RegularizedMAPInferenceJonathanN.Lee1AldoPacchiano2PeterBartlett23MichaelI.Jordan23Abstractinferenceinthesemodelshasmultipleapplications,rangingfromcomputervisio...
MaximumEntropy-RegularizedMulti-GoalReinforcementLearningRuiZhao12XudongSun1VolkerTresp12AbstractOneofthebiggestchallengesinRListomaketheagentlearnefficientlyinapplicationswithsparserewards.ToInMul...