个人简介

教育背景： 北京师范大学 学士 1998 国防科技大学 硕士 2006 上海大学 博士 所获学术荣誉及学术影响： 1.1998年度获长沙电力学院“优秀教师” 2.1998年度获系“优秀毕业实习指导教师” 3.2000年度获长沙电力学院“优秀教师” 4.2000年度获长沙电力学院“优质课奖” 5.2001年度获长沙电力学院“优秀教师” 6.2002年度获长沙电力学院“优秀教师” 7.2002年度获“华中电力集团奖教基金奖”三等奖 8.2003年度湖南省高等学校青年骨干教师培养对象

研究领域

算法与计算机软件；机器学习与智能控制

目前研究领域： 算法与计算机软件；机器学习与智能控制 已完成或已在承担的主要课题： 1.智能体在部分可观测马尔可夫环境下的激励学习研究，国家自然科学基金,2002-2005 2.多时间尺度风险敏感度MDP研究，理工大学科研基金 3.湖南省青年骨干教师培养对象，湖南省教育厅 4.1火力发电厂分布式数据采集与故障诊断系统，湖南省电力局科研项目（1998年），已结题，6万元，主持。 5.智能体在部分可观测马尔可夫环境下的激励学习研究，国家自然科学基金项目，在研，20万元，主研。 6.江西省地区电网负荷预测与分析系统，江西省电力总公司，已结题，50万元，主研。 7.教学管理软件的开发与推广，长沙电力学院教研项目（2000年），已结题，0.5万元，主研。 8.激励学习算法的收敛性研究，湖南省教委科研项目（2000年），已结题，0.5万元，主研。 9.激励学习智能体最优控制策略及其在微经济环境下的决策问题，湖南省教育厅科研基金项目（2007），在研，1万元，主持。 10.7、多时间参数风险敏感度MDP研究，长沙理工大学科研基金项目（2006），在研，3万元，主持。

近期论文

查看导师新发文章 （温馨提示：请注意重名现象，建议点开原文通过作者单位确认）

1.OptimalEqualityforMulti-TimeScaleRisk-SensitiveMarkovDecisionProcesses，ProceedingsinISCST,2005,Ningbo,China 2.AutomaticDiscoveryofSubgoalsforSequentialDecisionProblemsUsingPotentialFields，ProceedingsinICNC,2005:384-391. 3.求解POMDP的动态合并激励学习算法，计算机工程,No.19,2005 4.基于动态规划的激励学习遗忘算法，计算机工程与应用,2004,Vol40,No.20 5.ReinforcementLearningForgettingAlgorithmBasedonDynamicProgramming，JournalofComputerEngineeringandApplications,2004,Vol40,No.20. 6.AverageAsymptoticTemporalDifferenceLearningForgettingAlgorithmonEligibilityTrace,JournalofChangshaUniversityofElectricPower,2003(4). 7.ReinforcementLearningAlgorithmforSolvingRTDPwithVariationalEnvironment.ICGSTInternationalJournalonArtificialIntelligenceandMachineLearning(AIML),Volume(7),Issue(I),pp17-21. 8.ReinforcementLearningAlgorithmsBasedonmGAandEAwithPolicyIterations.LectureNotesinComputerScience(includingsubseriesLectureNotesinArtificialIntelligenceandLectureNotesinBioinformatics)Bio-InspiredComputationalIntelligenceandApplications-InternationalConferenceonLifeSystemModelingandSimulation,LSMS2007,Proceedingsv4688LNCS2007. 9.Risk-SensitiveReinforcementLearningAlgorithmswithGeneralizedAverageCriterion.AppliedMathematicsandMechanics-EnglishEdition,2007,V28,N3(MAR),pp405-416. 10.GlobalAttractorforKGSLatticeSystem.AppliedMathematicsandMechanics-EnglishEdition,2007,V28,N5(MAC),pp619-628. 11.FusedSarsa（lambda）LearningAlgorithmBased-onMulti-agent.JournalofComputerEngineeringandApplications,2008,44(4),pp182-183. 12.AutomaticDiscoveryofSubgoalsforSequentialDecisionProblemsUsingPotentialFields.2005InternationalConferenceonNaturalComputation/2005InternationalConferenceonFuzzySystemsandknowledgeDiscovery(ICNC'05-FSKD'05),IEEE.27-29August2005,Changsha,China.(LectureNotesinComputerScience,v3612,nPARTIII,AdvancesinNaturalComputation:FirstInternationalConference,ICNC2005.Proceedings,2005,pp384-391) 13.OptimalEqualityforMulti-TimeScaleRisk-SensitiveMarkovDecisionProcesses.ProceedingsintheInternationalSymposiumonComputerScienceandTechnology2005,Ningbo,China. 14.ReinforcementLearningAlgorithmBased-onPolicyIterationforSolvingRTDP.2006.8,ISAI’2006,Beijing,China. 15.U-Clustering:AReinforcementLearningAlgorithmBasedonUtilityClustering.JournalofComputerEngineeringandApplications,2005,No.20. 16.ReinforcementLearningForgettingAlgorithmBasedonDynamicProgramming.JournalofComputerEngineeringandApplications,2004,No.20. 17.TheDynamicMergeReinforcementLearningAlgorithmforSolvingPOMDP.JournalofComputerEngineering.2005,11. 18.Multi-TimeScaleRisk-SensitiveHierarchicalStructureControlProblem.DCABES2006,Hangzhou,China,2006.10. 19.UtilityClusteringforReinforcementLearningwithPartialObservability.InProceedingsofConferenceofChineseIntelligenceAutomatization,HongKong,China,2003.(IJCAI03). 20.AverageAsymptoticTemporalDifferenceLearningForgettingAlgorithmonEligibilityTrace,JournalofChangshaUniversityofElectricPower,2003(4). 21.NonlinearControlBasedonQ-learningAlgorithms.JournalofChangshaUniversityofElectricPower,Val.18,No.1,2003(1). 22.ARelativeValueIterationQ-LearningAlgorithmandItsConvergenceBased-onFiniteSamples.JournalofComputerResearchandDevelopment.Sept.2002,Vol.39,No.9. 23.OptimalityCostRelativeValueIterationQ-LearningAlgorithmBasedonFiniteSamples.JournalofComputerEngineeringandApplications,2002,No.14. 24.GeneralizeAverageAlgorithmforReinforcementLearningItsConvergence.JournalofComputerEngineeringandApplications,2002,No.20. 25.ReinforcementLearningAlgorithmBasedonaverageCostOptimizationforEachStage.JournalofComputerApplications,Val.22,No.4,2002(4). 26.ClassificationforUn-labeledContextBasedonMaximumExpectationLearningAlgorithm.Proceedingsof14thCDC(AnnulConferenceofControlandDecision,China). 27.ATD(lambda)LearningForgettingAlgorithm.Proceedingsof4thMachineandElectricEngineeringAssociationofHunan,China,Aug.2002. 28.DistributedReal-timeSystemforElectricPowerEnterpriseBasedonIntranet/Web.JournalofApplicationsoftheComputerSystems,2002(4). 29.TheUniformofSecurityPolicyinDistributedSystem.JournalofInformationEngineeringUniversity,2001.(ProceedingsofAnnualConferenceofChineseNetworksandInformationSecurity,Zhengzhou,China,2001). 30.DesignofDistributedRealTimeDatabaseSystemBasedonJDBC/Web.JournalofComputerDevelopmentandApplications.2001,No.36. 31.TheApplicationDelphiMulti-threadforDistributedRealtimeMulti-taskSystem.JournalofChangshaUniversityofElectricPower,Val.15,No.1,2001(1). 32.ComparingARPofIPv4withNeighborDiscoveryProtocolofIPv6.JournalofChangshaUniversityofElectricPower,Val.16,No.1,2001(1). 33.StudyandApplicationofDistributedRealTimeMultimediaDatabase.JournalofChangshaUniversityofElectricPower,Val.16,No.2,2001(2). 34.TheDesignofReal-timeMonitorDatabaseSystemBasedonDistributedHeterogeneousNetworksEnvironment.JournalofChangshaUniversityofElectricPower,Val.16,No.3,2001(3). 35.DistributedReal-timeMulti-taskSystemStudyandApplicationforMonitoringandSupervisinginElectricPowerPlant.Proceedingsof1stMachineandElectricEngineeringAssociationofHunan,China,Aug,1999. 36.ThePrinciplesandDesignMethodsforDomainServiceSystemofCampusNetworks.JournalofChangshaUniversityofElectricPower,Val.13,No.1,1998(1). 37.SecurityStudyforWindowsNTNetworkManagement.JournalofChangshaUniversityofElectricPower,Val.13,No.2,1998(2). 38.TheWeighedLorentzNormInequalityofGeneralizationMaximumOperator.AnnualofHunanMathematics,Val17,No.2,1997. 39.TheWeightedboundaryofOperatoranditsinterpolationonMixedLebesgueSpace.JournalofChangshaUniversityofElectricPower,Val.12,No.3,1997(3). 40.TheAlternativenessofNon-CommutativeandNon-CombinativeFractionalRing.JournalofChangshaUniversityofWaterResourcesandElectricPower,Val.8,No.2,1993(2). 41.TheCombinerTheoryofNon-CommutativeandNon-CombinativeFractionalRing.JournalofChangshaUniversityofWaterResourcesandElectricPower,Val.6,No.2,1991(2). 42.TheEquivalenceConditionsforReductionableElementsonComplexCommutativeBanachAlgebra.JournalofChangshaUniversityofWaterResourcesandElectricPower,Val.5,No.1,1990(1). 43.F-SetonUnitsquare-cubeundern-DimensionEuclidSpace.JournalofChangshaUniversityofWaterResourcesandElectricPower,Val.5,No.2,1990(2).