{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T16:24:14Z","timestamp":1780071854414,"version":"3.54.0"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"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":["62273234"],"award-info":[{"award-number":["62273234"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tsmc.2023.3344883","type":"journal-article","created":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T18:58:40Z","timestamp":1705085920000},"page":"2368-2378","source":"Crossref","is-referenced-by-count":10,"title":["Reinforcement Learning Controller Design for Discrete-Time-Constrained Nonlinear Systems With Weight Initialization Method"],"prefix":"10.1109","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4058-0447","authenticated-orcid":false,"given":"Jiahui","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4277-1263","authenticated-orcid":false,"given":"Jingcheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4361-9378","authenticated-orcid":false,"given":"Yanjiu","family":"Zhong","sequence":"additional","affiliation":[{"name":"Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7467-4898","authenticated-orcid":false,"given":"Jun","family":"Rao","sequence":"additional","affiliation":[{"name":"Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9856-2148","authenticated-orcid":false,"given":"Shunyu","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.096"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3004204"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3001715"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3247466"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3220026"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3105663"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3247888"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-090419-075625"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-021-06177-3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3001840"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977318"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5955"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2276"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3024161"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5132"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619113"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2920206"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.11.034"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2027233"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2417170"},{"key":"ref24","first-page":"1587","article-title":"Addressing function approximation error in actor\u2013critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-021-0473-6"},{"key":"ref26","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref27","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. Thirteen. Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref28","article-title":"What matters in on-policy reinforcement learning? A large-scale empirical study","author":"Andrychowicz","year":"2020","journal-title":"arXiv:2006.05990"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/asjc.2552"},{"key":"ref30","volume-title":"Nonlinear Model Predictive Control","volume":"26","author":"Allg\u00f6wer","year":"2012"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3009580"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPEL.2021.3085679"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2937002"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2982585"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref36","first-page":"1","volume-title":"Gurobi Optimizer Reference Manual","year":"2020"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/10474538\/10398273.pdf?arnumber=10398273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T13:18:41Z","timestamp":1711459121000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10398273\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":36,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2023.3344883","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}