{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:12:13Z","timestamp":1780672333794,"version":"3.54.1"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Shandong Province Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.neucom.2026.133899","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T09:58:01Z","timestamp":1778579881000},"page":"133899","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Simplified reinforcement learning for optimal tracking control of input-constrained nonlinear systems using neural networks"],"prefix":"10.1016","volume":"693","author":[{"given":"Chaoyue","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2952-4911","authenticated-orcid":false,"given":"Fei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.neucom.2026.133899_bib0005","doi-asserted-by":"crossref","first-page":"1365","DOI":"10.1109\/TAC.2019.2924176","article-title":"Performance recovery of dynamic feedback-linearization methods for multivariable nonlinear systems","volume":"65","author":"Wu","year":"2019","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.neucom.2026.133899_bib0010","series-title":"1991 American Control Conference","first-page":"649","article-title":"Systematic design of adaptive controllers for feedback linearizable systems","author":"Kanellakopoulos","year":"1991"},{"issue":"10","key":"10.1016\/j.neucom.2026.133899_bib0015","doi-asserted-by":"crossref","first-page":"2324","DOI":"10.1109\/TAC.2008.2006821","article-title":"Performance recovery of feedback-linearization-based designs","volume":"53","author":"Freidovich","year":"2008","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.neucom.2026.133899_bib0020","series-title":"Sliding Mode Control and Observation","volume":"vol. 10","author":"Shtessel","year":"2014"},{"issue":"1","key":"10.1016\/j.neucom.2026.133899_bib0025","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1007\/s40435-020-00638-7","article-title":"Review of sliding mode based control techniques for control system applications","volume":"9","author":"Gambhire","year":"2021","journal-title":"Int. J. Dyn. Control"},{"issue":"9","key":"10.1016\/j.neucom.2026.133899_bib0030","doi-asserted-by":"crossref","first-page":"1820","DOI":"10.1109\/TSMC.2018.2875947","article-title":"Adaptive neural backstepping control design for a class of nonsmooth nonlinear systems","volume":"49","author":"Zhao","year":"2018","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"10.1016\/j.neucom.2026.133899_bib0035","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.isatra.2021.06.009","article-title":"Adaptive backstepping quantized control for a class of unknown nonlinear systems","volume":"125","author":"Aslmostafa","year":"2022","journal-title":"ISA Trans."},{"key":"10.1016\/j.neucom.2026.133899_bib0040","series-title":"Optimal Control and Viscosity Solutions of Hamilton-Jacobi-Bellman Equations","volume":"vol. 12","author":"Bardi","year":"1997"},{"key":"10.1016\/j.neucom.2026.133899_bib0045","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1016\/j.neunet.2015.08.007","article-title":"Reinforcement learning solution for HJB equation arising in constrained optimal control problem","volume":"71","author":"Luo","year":"2015","journal-title":"Neural Netw."},{"issue":"3731","key":"10.1016\/j.neucom.2026.133899_bib0050","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1126\/science.153.3731.34","article-title":"Dynamic programming","volume":"153","author":"Bellman","year":"1966","journal-title":"Science"},{"key":"10.1016\/j.neucom.2026.133899_bib0055","article-title":"Approximate dynamic programming for real-time control and neural modeling","author":"Werbos","year":"1992"},{"key":"10.1016\/j.neucom.2026.133899_bib0060","series-title":"Proceedings of the 28th IEEE Conference on Decision and Control","first-page":"260","article-title":"Neural networks for control and system identification","author":"Werbos","year":"1989"},{"issue":"6","key":"10.1016\/j.neucom.2026.133899_bib0065","doi-asserted-by":"crossref","first-page":"2483","DOI":"10.1109\/TNNLS.2020.3006080","article-title":"Automatic generation control based on multiple neural networks with actor-critic strategy","volume":"32","author":"Xi","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"6","key":"10.1016\/j.neucom.2026.133899_bib0070","doi-asserted-by":"crossref","first-page":"2101","DOI":"10.1109\/TFUZZ.2021.3075501","article-title":"Robust actor-critic learning for continuous-time nonlinear systems with unmodeled dynamics","volume":"30","author":"Yang","year":"2021","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"10.1016\/j.neucom.2026.133899_bib0075","series-title":"Advances in Neural Information Processing Systems","article-title":"Actor-critic algorithms","volume":"vol. 12","author":"Konda","year":"1999"},{"key":"10.1016\/j.neucom.2026.133899_bib0080","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106737","article-title":"ADP-based fault-tolerant consensus control for multiagent systems with irregular state constraints","volume":"180","author":"Guo","year":"2024","journal-title":"Neural Netw."},{"issue":"1","key":"10.1016\/j.neucom.2026.133899_bib0085","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1109\/TSMC.2020.3042876","article-title":"Adaptive dynamic programming for control: a survey and recent advances","volume":"51","author":"Liu","year":"2020","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"1","key":"10.1016\/j.neucom.2026.133899_bib0090","first-page":"85","article-title":"Adaptive dynamic programming for networked control systems under communication constraints: a survey of trends and techniques","volume":"1","author":"Wang","year":"2022","journal-title":"Int. J. Netw. Dyn. Intell."},{"key":"10.1016\/j.neucom.2026.133899_bib0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.112243","article-title":"Reinforcement learning-based secure tracking control for nonlinear interconnected systems: an event-triggered solution approach","volume":"161","author":"Qin","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.133899_bib0100","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: a survey","volume":"4","author":"Kaelbling","year":"1996","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/j.neucom.2026.133899_bib0105","series-title":"Reinforcement Learning and Optimal Control","volume":"vol. 1","author":"Bertsekas","year":"2019"},{"issue":"1","key":"10.1016\/j.neucom.2026.133899_bib0110","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000086","article-title":"Model-based reinforcement learning: a survey","volume":"16","author":"Moerland","year":"2023","journal-title":"Found. Trends\u00ae Mach. Learn."},{"key":"10.1016\/j.neucom.2026.133899_bib0115","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1007\/s10462-025-11439-9","article-title":"Reinforcement learning for single-agent to multi-agent systems: from basic theory to industrial application progress, a survey","volume":"59","author":"Zhang","year":"2026","journal-title":"Artif. Intell. Rev."},{"issue":"4","key":"10.1016\/j.neucom.2026.133899_bib0120","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1007\/s12555-022-0223-4","article-title":"Adaptive dynamic programming-based adaptive optimal tracking control of a class of strict-feedback nonlinear system","volume":"21","author":"Zhao","year":"2023","journal-title":"Int. J. Control Autom. Syst."},{"issue":"7","key":"10.1016\/j.neucom.2026.133899_bib0125","doi-asserted-by":"crossref","first-page":"3034","DOI":"10.1109\/TNNLS.2020.3009214","article-title":"Reinforcement learning-based optimal tracking control of an unknown unmanned surface vehicle","volume":"32","author":"Wang","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"9","key":"10.1016\/j.neucom.2026.133899_bib0130","doi-asserted-by":"crossref","first-page":"3689","DOI":"10.1109\/TCSI.2022.3177407","article-title":"Distributed optimal tracking control of discrete-time multiagent systems via event-triggered reinforcement learning","volume":"69","author":"Peng","year":"2022","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"10.1016\/j.neucom.2026.133899_bib0135","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1016\/j.ins.2022.11.109","article-title":"Adaptive reinforcement learning optimal tracking control for strict-feedback nonlinear systems with prescribed performance","volume":"621","author":"Huang","year":"2023","journal-title":"Inf. Sci."},{"key":"10.1016\/j.neucom.2026.133899_bib0140","series-title":"Reinforcement Learning for Sequential Decision and Optimal Control","author":"Li","year":"2023"},{"key":"10.1016\/j.neucom.2026.133899_bib0145","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.neucom.2021.01.096","article-title":"Identification and optimal control of nonlinear systems using recurrent neural networks and reinforcement learning: an overview","volume":"438","author":"Perrusqu\u00eda","year":"2021","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.neucom.2026.133899_bib0150","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1109\/TSMC.2023.3302656","article-title":"Barrier-critic adaptive robust control of nonzero-sum differential games for uncertain nonlinear systems with state constraints","volume":"54","author":"Qin","year":"2023","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"9","key":"10.1016\/j.neucom.2026.133899_bib0155","doi-asserted-by":"crossref","first-page":"7879","DOI":"10.1109\/TIE.2019.2946545","article-title":"Optimized formation control using simplified reinforcement learning for a class of multiagent systems with unknown dynamics","volume":"67","author":"Wen","year":"2019","journal-title":"IEEE Trans. Ind. Electron."},{"key":"10.1016\/j.neucom.2026.133899_bib0160","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.ins.2019.12.039","article-title":"Simplified optimized control using reinforcement learning algorithm for a class of stochastic nonlinear systems","volume":"517","author":"Wen","year":"2020","journal-title":"Inf. Sci."},{"issue":"1","key":"10.1016\/j.neucom.2026.133899_bib0165","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1109\/TNNLS.2022.3177461","article-title":"Game-based backstepping design for strict-feedback nonlinear multi-agent systems based on reinforcement learning","volume":"35","author":"Long","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.133899_bib0170","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1016\/j.ins.2022.05.048","article-title":"Optimized tracking control based on reinforcement learning for a class of high-order unknown nonlinear dynamic systems","volume":"606","author":"Wen","year":"2022","journal-title":"Inf. Sci."},{"key":"10.1016\/j.neucom.2026.133899_bib0175","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128382","article-title":"Observer-based time-varying formation-containment tracking of general linear multi-agent systems with input saturation","volume":"608","author":"Zhang","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133899_bib0180","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127575","article-title":"Sliding-mode surface-based adaptive optimal nonzero-sum games for saturated nonlinear multi-player systems with identifier-critic networks","volume":"584","author":"Liu","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133899_bib0185","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.112221","article-title":"Observer based fault tolerant control design for saturated nonlinear systems with full state constraints via a novel event-triggered mechanism","volume":"161","author":"Qin","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.133899_bib0190","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.isatra.2017.01.018","article-title":"Finite-time stability and stabilization for stochastic markov jump systems with mode-dependent time delays","volume":"68","author":"Yan","year":"2017","journal-title":"ISA Trans."},{"issue":"7","key":"10.1016\/j.neucom.2026.133899_bib0195","doi-asserted-by":"crossref","first-page":"1780","DOI":"10.1016\/j.automatica.2014.05.011","article-title":"Optimal tracking control of nonlinear partially-unknown constrained-input systems using integral reinforcement learning","volume":"50","author":"Modares","year":"2014","journal-title":"Automatica"},{"issue":"5","key":"10.1016\/j.neucom.2026.133899_bib0200","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1016\/j.isatra.2013.04.004","article-title":"A policy iteration approach to online optimal control of continuous-time constrained-input systems","volume":"52","author":"Modares","year":"2013","journal-title":"ISA Trans."},{"key":"10.1016\/j.neucom.2026.133899_bib0205","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neucom.2018.09.011","article-title":"Integral reinforcement learning based decentralized optimal tracking control of unknown nonlinear large-scale interconnected systems with constrained-input","volume":"323","author":"Liu","year":"2019","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.neucom.2026.133899_bib0210","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1109\/TNNLS.2018.2832025","article-title":"Optimal synchronization control of multiagent systems with input saturation via off-policy reinforcement learning","volume":"30","author":"Qin","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.133899_bib0215","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1016\/j.isatra.2024.09.018","article-title":"Adaptive critic design for safety-optimal FTC of unknown nonlinear systems with asymmetric constrained-input","volume":"155","author":"Zhang","year":"2024","journal-title":"ISA Trans."},{"issue":"3","key":"10.1016\/j.neucom.2026.133899_bib0220","doi-asserted-by":"crossref","first-page":"2681","DOI":"10.1007\/s11063-019-10029-5","article-title":"An analysis of IRL-based optimal tracking control of unknown nonlinear systems with constrained input","volume":"50","author":"Liu","year":"2019","journal-title":"Neural Process. Lett."},{"key":"10.1016\/j.neucom.2026.133899_bib0225","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1016\/j.neunet.2022.10.025","article-title":"Event-triggered adaptive dynamic programming for decentralized tracking control of input constrained unknown nonlinear interconnected systems","volume":"157","author":"Wu","year":"2023","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.133899_bib0230","series-title":"Adaptive Dynamic Programming for Control: Algorithms and Stability","author":"Zhang","year":"2013"},{"issue":"5","key":"10.1016\/j.neucom.2026.133899_bib0235","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1016\/j.automatica.2004.11.034","article-title":"Nearly optimal control laws for nonlinear systems with saturating actuators using a neural network HJB approach","volume":"41","author":"Abu-Khalaf","year":"2005","journal-title":"Automatica"},{"key":"10.1016\/j.neucom.2026.133899_bib0240","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.neunet.2022.08.010","article-title":"Synergetic learning structure-based neuro-optimal fault tolerant control for unknown nonlinear systems","volume":"155","author":"Xia","year":"2022","journal-title":"Neural Netw."},{"issue":"17","key":"10.1016\/j.neucom.2026.133899_bib0245","doi-asserted-by":"crossref","first-page":"2686","DOI":"10.1002\/rnc.3018","article-title":"Online adaptive algorithm for optimal control with integral reinforcement learning","volume":"24","author":"Vamvoudakis","year":"2014","journal-title":"Int. J. Robust Nonlinear Control"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226012968?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226012968?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T14:38:59Z","timestamp":1780670339000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226012968"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":49,"alternative-id":["S0925231226012968"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133899","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Simplified reinforcement learning for optimal tracking control of input-constrained nonlinear systems using neural networks","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133899","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133899"}}