強化學習與分層強化學習相關知識基礎概述目錄TOC\o"1-3"\h\u3356強化學習與分層強化學習相關知識基礎概述 [26]。參考文獻鄭浩峻.足式機器人生物控制方法與應用.北京:清華大學出版社,2011.Print.程品.四足仿生機器人控制系統(tǒng)的研究與設計[D].湖北:華中科技大學,2014.DOI:10.7666/d.D610166.周坤,李川,李超,朱秋國.面向未知復雜地形的四足機器人運動規(guī)劃方法[J].機械工程學報,2020,56(02):210-219.張帥帥.復雜地形環(huán)境中四足機器人行走方法研究[D].山東大學,2016.楊鈞杰,孫浩,王常虹,陳曉東.四足機器人研究綜述[J].導航定位與授時,2019,6(05):61-73.JeneltenF,HwangboJ,TresoldiF,etal.Dynamiclocomotiononslipperyground[J]IEEERoboticsandAutomationLetters,2019,4(4):4170-4176．JinB,SunC,ZhangA,etal.Jointtorqueestimationtowarddynamicandcompliantcontrolforgear-driventorquesensorlessquadrupedrobot[C]//AraiF.2019IEEE/RSJInternationalConferenceonIntelligentRobotsandSystems(IROS).MACAO:IEEE,2019:4630-4637．KolvenbachH,HamppE,BartonP,etal.Towardsjumpinglocomotionforquadrupedrobotsonthemoon[C]//AraiF.2019IEEE/RSJInternationalConferenceonIntelligentRobotsandSystems(IROS).MACAO:IEEE,2019:5459-5466．SaputraAA,TodaY,TakesueN,etal.Anovelcapabilitiesofquadrupedrobotmovingthroughverticalladderwithouthandrailsupport[C]//AraiF.2019IEEE/RSJInternationalConferenceonIntelligentRobotsandSystems(IROS).MACAO:IEEE,2019:1448-1453．LeeYH,LeeYH,LeeH,etal.Whole-bodymotionandlandingforcecontrolforquadrupedalstairclimbing[C]//AraiF.2019IEEE/RSJInternationalConferenceonIntelligentRobotsandSystems(IROS).MACAO:IEEE,2019:4746-4751．JeneltenF,HwangboJ,TresoldiF,etal.Dynamiclocomotiononslipperyground[J]IEEERoboticsandAutomationLetters,2019,4(4):4170-4176．張偉,譚文浩,李貽斌.基于深度強化學習的四足機器人運動控制發(fā)展現(xiàn)狀與展望[J].山東大學學報(醫(yī)學版),2020,58(08):61-66.朱秋國.淺談四足機器人的發(fā)展歷史、現(xiàn)狀與未來[J].杭州科技,2017,(2):47-50.DOI:10.3969/j.issn.1004-2651.2017.01.013.李川.四足仿生機器人跑跳運動規(guī)劃與控制[D].浙江大學,2017.劉永,周川,郭健,許威.四足機器人單步急停穩(wěn)定控制策略[J].南京理工大學學報,2020,44(03):259-265.李田法.電機驅動四足機器人能耗優(yōu)化與高速運動步態(tài)規(guī)劃研究[D].山東大學,2020.王艷琴,許威,周川,郭健.基于質心調整的四足機器人轉彎步態(tài)規(guī)劃[J/OL].控制工程:1-6[2021-03-30]./10.14107/ki.kzgc.20200271.陳騰.基于力控的四足機器人高動態(tài)運動控制方法研究[D].山東大學,2020.俞文雅,陶紅武,曾順,譚躍剛.四足機器人斜坡對角小跑運動控制研究[J].武漢科技大學學報,2021,44(01):60-67.周文吉,俞揚.分層強化學習綜述[J].智能系統(tǒng)學報,2017,12(5):590-594.DOI:10.11992/tis.201706031.PARRR,RUSSELLS.Reinforcementlearningwithhierarchiesofmachines[C]//AdvancesinNeuralInformationProcessingSystems.Colorado,USA,1998:1043－1049.SUTTONRS,PRECUPDSINGHS.BetweenMDPsandsemi-MDPs:aframeworkfortemporalabstractioninreinforcementlearning[J].Artificialintelligence,1999,112(1/2):181－211．DIETTERICHG.HierarchicalreinforcementlearningwiththeMAXQvaluefunctiondecomposition[J].Journalofartificialintelligenceresear-ch,2000,13:227－303．PIERRE-LUCBACON,JEANHARB.Theoption-criticarchitecture[C]//InProceedingof31thAAAIConferenceonArtificialIntelligence.SanFrancisco,USA,2017:1726－1734．VEZHNEVETSAS,OSINDEROS,SCHAULT,etal.FeUdalnetworksforhierarchicalreinforcementlearning[C]//InProceedingsofthe34thInternationalConferenceonMachineLearning.Sydney,Australia,2017:3540－3549．MNIHV,KAVUKCUOGLUK,SILVERD,etal.Human-levelcontrolthroughdeepreinforcementlearning[J].Nature,2015,518(2):529－533．PengXB,AbbeelP,LevineS,etal.Deepmimic:example-guideddeepreinforcementlearningofphysicsbasedcharacterskills[J].ACMTransactionsonGraphics(TOG),2018,37(4):1-14．TanJ,ZhangT,CoumansE,etal.Sim-to-real:learningagilelocomotionforquadrupedrobots[J].arXiv:1804.10332,2018.HaarnojaT,ZhouA,AbbeelP,etal.Softactor-critic:off-policymaximumentropydeepreinforcementlearningwithastochasticactor[J].arXiv:1801.01290,2018．JainD,IscenA,CaluwaertsK.Hierarchicalreinforcementlearningforquadrupedlocomotion[J].arXiv:1905.08926,2019.崔俊文,劉自紅,石磊,等.基于分層學習的四足機器人運動自適應控制模型[J].計算機測量與控制,2020,28(1):105-110.DOI:10.16526/ki.11-4762/tp.2020.01.023.高陽,陳世福,陸鑫.強化學習研究綜述[J].自動化學報,2004,30(1):86-100.Watkins,Christopher,JDayan."Q-learning."MachineLearning8.3-4(1992):279-91.Web.SuttonRS,Barto,AG.ReinforcementLearning:AnIntroduction[J].IEEETransactionsonNeuralNetworks,1998,9(5):1045-9227.WangYD,SunJ,HeHB,SunCY.Deterministicpolicygradientwithintegralcompensatorforrobustquadrotorcontrol[J].IEEETransactionsonSystems,Man,andCybernetics:Systems,2019.HwangboJ,LeeJ,DosovitskiyA,etal.Learningagileanddynamicmotorskillsforleggedrobots[J].ScienceRobotics,2019,4(26):eaau5872．FransK,HoJ,ChenX,etal.Metalearningsharedhierarchies[J].arXiv:1710.09767,2017.Mania,Horia,AureliaGuy,andBenjaminRecht."SimpleRandomSearchProvidesaCompetitiveApproachtoReinforcementLearning."ArX(2018):ArX,Mar19,2018.Web.邢立波.基于分層強化學習算法的稀疏獎勵問題研究[D].華南理工大學,2020.陳騰.基于力控的四足機器人高動態(tài)運動控制方法研究[D].山東大學,2020.Kimura,Fukuoka,Hada,Takase,andKimura,H."Three-dimensionalAdaptiveDynamicWalkingofaQuadruped-RollingMotionFeed