{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T05:01:19Z","timestamp":1768971679349,"version":"3.49.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91748122"],"award-info":[{"award-number":["91748122"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["17JC1400603"],"award-info":[{"award-number":["17JC1400603"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["18ZR1442700"],"award-info":[{"award-number":["18ZR1442700"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2904910","type":"journal-article","created":{"date-parts":[[2019,3,19]],"date-time":"2019-03-19T20:13:14Z","timestamp":1553026394000},"page":"41799-41810","source":"Crossref","is-referenced-by-count":14,"title":["Hierarchical Intermittent Motor Control With Deterministic Policy Gradient"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9976-6927","authenticated-orcid":false,"given":"Haibo","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2179-0713","authenticated-orcid":false,"given":"Yaoru","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1897-2874","authenticated-orcid":false,"given":"Daming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref38","first-page":"1","article-title":"Subgoal discovery for hierarchical reinforcement learning using learned policies","author":"goel","year":"2003","journal-title":"Proc FLAIRS Conf"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553471"},{"key":"ref32","first-page":"1","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","first-page":"1","article-title":"Q-prop: Sample-efficient policy gradient with an off-policy critic","author":"gu","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref30","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022140919877"},{"key":"ref34","first-page":"1","article-title":"Feudal reinforcement learning","author":"dayan","year":"1992","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/S0001-6918(98)00029-8"},{"key":"ref62","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1038\/nature11129","article-title":"Neural population dynamics during reaching","volume":"487","author":"churchland","year":"2012","journal-title":"Nature"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1038\/nn963"},{"key":"ref28","first-page":"2944","article-title":"Learning continuous control policies by stochastic value gradients","author":"heess","year":"2015","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2791469"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1038\/35037588","article-title":"Learning of action through adaptive combination of motor primitives","volume":"407","author":"thoroughman","year":"2000","journal-title":"Nature"},{"key":"ref20","first-page":"1","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nature25978"},{"key":"ref24","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref26","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref50","author":"lakshminarayanan","year":"2016","journal-title":"Option discovery in hierarchical reinforcement learning using spatio-temporal clustering"},{"key":"ref51","first-page":"1","article-title":"Hierarchical and interpretable skill acquisition in multi-task reinforcement learning","author":"shu","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref59","first-page":"1","article-title":"Design principles of the hippocampal cognitive map","author":"stachenfeld","year":"2014","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2051031"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00282"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2008.08.011"},{"key":"ref55","first-page":"1","article-title":"Iterative linear quadratic regulator design for nonlinear biological movement systems","author":"li","year":"2004","journal-title":"Proc 1st Int Conf Inform Control Automat Robot (ICINCO)"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/PIC.2017.8359558"},{"key":"ref53","first-page":"56","article-title":"Intemittent control with reinforcement learning","author":"shi","year":"2017","journal-title":"Proc Int Conf Progr Inform Comput (PIC)"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2018.8665177"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1049\/ip-cta:19990504"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-010-0416-4"},{"key":"ref40","first-page":"3540","article-title":"FeUdal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2011.0212"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.2010.194712"},{"key":"ref14","first-page":"2094","article-title":"Deep reinforcement learning with double Q-Learning","author":"van hasselt","year":"2016","journal-title":"Proc Conf Artif Intell"},{"key":"ref15","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","first-page":"1","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref17","author":"li","year":"2017","journal-title":"Deep reinforcement learning An overview"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref19","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2000.0733"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2002.1258"},{"key":"ref6","author":"heess","year":"2016","journal-title":"Learning and transfer of modulated locomotor controllers"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-neuro-062111-150509"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2013.00012"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-5465-6_9"},{"key":"ref49","first-page":"1553","article-title":"A deep hierarchical approach to lifelong learning in minecraft","author":"tessler","year":"2016","journal-title":"Proc Nat Conf Artif Intell"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2015.03.012"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2805379"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/461"},{"key":"ref48","first-page":"6550","article-title":"Towards generalization and simplicity in continuous control","author":"rajeswaran","year":"2017","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref47","first-page":"1","article-title":"The option-critic architecture","author":"bacon","year":"2017","journal-title":"Proc Nat Conf Artif Intell"},{"key":"ref42","author":"heess","year":"2016","journal-title":"Learning and transfer of modulated locomotor controllers"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1145\/3072959.3073602","article-title":"Deeploco: Dynamic locomotion skills using hierarchical deep reinforcement learning","volume":"36","author":"peng","year":"2017","journal-title":"ACM Trans Graph"},{"key":"ref44","first-page":"1","article-title":"Strategic attentive writer for learning macro-actions","author":"vezhnevets","year":"2016","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref43","first-page":"1","article-title":"Stochastic neural networks for hierarchical reinforcement learning","author":"florensa","year":"2017","journal-title":"Proc Int Conf Learn Represent"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08671473.pdf?arnumber=8671473","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T07:23:27Z","timestamp":1643268207000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8671473\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2904910","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}