{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:58:57Z","timestamp":1772121537923,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52275020"],"award-info":[{"award-number":["52275020"]}],"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":["72101194"],"award-info":[{"award-number":["72101194"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tai.2022.3215671","type":"journal-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T17:45:33Z","timestamp":1667497533000},"page":"734-743","source":"Crossref","is-referenced-by-count":8,"title":["Design of Observer-Based Control With Residual Generator Using Actor\u2013Critic Reinforcement Learning"],"prefix":"10.1109","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8477-7877","authenticated-orcid":false,"given":"Lu","family":"Qian","sequence":"first","affiliation":[{"name":"School of Transportation and Logistics Engineering, Wuhan University of Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4568-6814","authenticated-orcid":false,"given":"Xingwei","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Digital Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"}]},{"given":"Peifeng","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Digital Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"}]},{"given":"Zhenwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Digital Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2953-9996","authenticated-orcid":false,"given":"Yaqiong","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Transportation and Logistics Engineering, Wuhan University of Technology, Wuhan, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2897583"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2010.05.005"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2019.07.015"},{"key":"ref34","first-page":"799","article-title":"Autonomous helicopter flight via reinforcement learning","author":"kim","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3029946"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2010.2043839"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2999323"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1971.1099826"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3134082"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.2992003"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2018.09.016"},{"key":"ref33","first-page":"623","article-title":"Reinforcement learning for CPG-driven biped robot","volume":"4","author":"mori","year":"2004","journal-title":"AAAI"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2009.02.011"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(97)00043-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3066565"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3105621"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.2989708"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2477810"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071292"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2014.2322778"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2015.2417501"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2019.2949368"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.05.037"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(88)90073-8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2022.101609"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2013.2273477"},{"key":"ref42","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2886735"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2577623"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.10.047"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2007.05.008"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2018.12.048"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0967-0661(99)00181-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2019.2892678"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3091038"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2017.01.020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2016.09.015"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2870075"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10190086\/09924571.pdf?arnumber=9924571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:08:56Z","timestamp":1755911336000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9924571\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":42,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tai.2022.3215671","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}