简介：Amultiresolutionstate-spacediscretizationmethodwithpseudorandomgriddingisdevelopedfortheepisodicunsupervisedlearningmethodofQ-learning.Itisusedasthelearningagentforclosed-loopcontrolofmorphingorhighlyreconfigurablesystems.Thispaperdevelopsamethodwherebyastate-spaceisadaptivelydiscretizedbyprogressivelyfinerpseudorandomgridsaroundtheregionsofinterestwithinthestateorlearningspaceinanefforttobreaktheCurseofDimensionality.Utilityofthemethodi...

简介：这篇论文基于多客观的最佳的控制系统建议非线性的控制器和一个大阶段角度津贴设计方法的一种新类型。与建议方法，系统的性能变得比原来的系统的好。然后，雷达伺服系统的一个例子与大阶段角度津贴被设计多客观的最佳的设计方法。最后，性能基于计算机模拟证明多客观的最佳的系统比线性最佳的系统优异。

简介：Aprimarychallengeofagent-basedpolicylearningincomplexanduncertainenvironmentsisescalatingcomputationalcomplexitywiththesizeofthetaskspace(actionchoicesandworldstates)andthenumberofagents.Nonetheless,thereisampleevidenceinthenaturalworldthathigh-functioningsocialmammalslearntosolvecomplexproblemswithease,bothindividuallyandcooperatively.Thisabilitytosolvecomputationallyintractableproblemsstemsfrombothbraincircuitsforhierarchicalrepresentation...