{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T15:54:07Z","timestamp":1770738847193,"version":"3.49.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation (NNSF) of China","doi-asserted-by":"publisher","award":["61573154"],"award-info":[{"award-number":["61573154"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012245","name":"Science and Technology Planning Project of Guangdong Province","doi-asserted-by":"publisher","award":["2015A010106003"],"award-info":[{"award-number":["2015A010106003"]}],"id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012245","name":"Science and Technology Planning Project of Guangdong Province","doi-asserted-by":"publisher","award":["2017A010101009"],"award-info":[{"award-number":["2017A010101009"]}],"id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3011194","type":"journal-article","created":{"date-parts":[[2020,7,22]],"date-time":"2020-07-22T20:54:42Z","timestamp":1595451282000},"page":"134456-134467","source":"Crossref","is-referenced-by-count":13,"title":["Reinforcement Q-Learning Incorporated With Internal Model Method for Output Feedback Tracking Control of Unknown Linear Systems"],"prefix":"10.1109","volume":"8","author":[{"given":"Cong","family":"Chen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6148-6783","authenticated-orcid":false,"given":"Weijie","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Guangyue","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6066-3979","authenticated-orcid":false,"given":"Yunjian","family":"Peng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1002\/asjc.161","article-title":"On a robust synchronization problem via internal model approach","volume":"12","author":"sun","year":"2010","journal-title":"Asian J Control"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1968.1098829"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.05.027"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2901889"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/acs.2830"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2014.2322778"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.07.004"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/MCS.2012.2214134","article-title":"Reinforcement learning and feedback control: Using natural decision methods to design optimal adaptive controllers","volume":"32","author":"lewis","year":"2012","journal-title":"IEEE Control Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.02.015"},{"key":"ref34","article-title":"Reinforcement Q-learning algorithm for $H_\\infty$ tracking control of unknown discrete-time linear systems","author":"peng","year":"2019","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"ref10","author":"sutton","year":"1998","journal-title":"Reinforcement Learning"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.07.098"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2915376"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2017.1352104"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/37.126844","article-title":"Reinforcement learning is direct adaptive optimal control","volume":"12","author":"sutton","year":"1992","journal-title":"IEEE Control Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejcon.2013.05.017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2019.2948431"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.2966418"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.08.017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3766"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1109\/TNNLS.2013.2257843","article-title":"Dynamic learning from adaptive neural network control of a class of nonaffine nonlinear systems","volume":"25","author":"dai","year":"2014","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/a12060121"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198537953.001.0001","author":"lancaster","year":"1995","journal-title":"Algebraic Riccati Equations"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0142331215620267"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2870075"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2429555"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/app9091807"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.06.051"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1971.1099755"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2170219"},{"key":"ref1","author":"lewis","year":"2015","journal-title":"Optimal Control"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.096"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.111"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2317301"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718683"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2384016"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(76)90006-6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2010.2043839"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.01.029"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2015.0977"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09146286.pdf?arnumber=9146286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T15:32:06Z","timestamp":1723303926000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9146286\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3011194","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}