{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:34:51Z","timestamp":1787013291605,"version":"3.56.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0101400"],"award-info":[{"award-number":["2018AAA0101400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province of China","doi-asserted-by":"publisher","award":["BK20202006"],"award-info":[{"award-number":["BK20202006"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073225"],"award-info":[{"award-number":["62073225"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61921004"],"award-info":[{"award-number":["61921004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173251"],"award-info":[{"award-number":["62173251"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/tnnls.2022.3156287","type":"journal-article","created":{"date-parts":[[2022,4,13]],"date-time":"2022-04-13T15:30:55Z","timestamp":1649863855000},"page":"9161-9170","source":"Crossref","is-referenced-by-count":26,"title":["Hybrid Reinforcement Learning for Optimal Control of Non-Linear Switching System"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1347-4032","authenticated-orcid":false,"given":"Xiaofeng","family":"Li","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6737-1381","authenticated-orcid":false,"given":"Lu","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2510-1188","authenticated-orcid":false,"given":"Lei","family":"Xue","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9269-334X","authenticated-orcid":false,"given":"Changyin","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/9.654885"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2514\/6.2013-4635"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.03.019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(04)00223-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/.2005.1467024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/0020717021000023825"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-78929-1_42"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.821417"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2010.2085573"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2178649"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2509421"},{"key":"ref46","article-title":"Multi-pass Q-networks for deep reinforcement learning with parameterised action spaces","author":"bester","year":"2019","journal-title":"arXiv 1905 04388"},{"key":"ref45","article-title":"Parametrized deep Q-networks learning: Reinforcement learning with discrete-continuous hybrid action space","author":"xiong","year":"2018","journal-title":"arXiv 1810 06394"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963780"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2018.2823699"},{"key":"ref42","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref41","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume":"16","author":"abadi","year":"2016","journal-title":"Proc 5th USENIX Conf Operating Syst Design Implementation"},{"key":"ref44","article-title":"Deep reinforcement learning in parameterized action space","author":"hausknecht","year":"2015","journal-title":"arXiv 1511 04143"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10226"},{"key":"ref49","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn (ICML)"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"4401","DOI":"10.1109\/CDC.2002.1185065","article-title":"Optimal control of switched autonomous systems","volume":"4","author":"xu","year":"2002","journal-title":"Proc 41st IEEE Conf Decis Control"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10626-014-0187-5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.nahs.2007.11.010"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2116156"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2007.903366"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2250076"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2012.2224257"},{"key":"ref40","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2303139"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1989.4790360"},{"key":"ref37","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-020-10278-9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2541020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2027233"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2017.04.015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2635586"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2514\/1.C031490"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0017-8"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719512"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/72.914523"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926614"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2020.1003486"},{"key":"ref20","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.056"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.03.022"},{"key":"ref29","first-page":"62","article-title":"Optimal tracking control for a class of nonlinear discrete-time systems with time delays based on heuristic dynamic programming","volume":"22","author":"zhang","year":"2011","journal-title":"IEEE Trans Neural Netw"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10299535\/09756440.pdf?arnumber=9756440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T14:28:17Z","timestamp":1699885697000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9756440\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":50,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3156287","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}