{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T12:07:30Z","timestamp":1790251650449,"version":"4.1.0"},"reference-count":39,"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"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["ISA Transactions"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.isatra.2026.09.025","type":"journal-article","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T08:50:11Z","timestamp":1789721411000},"update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["Data-driven preview Q-learning for H\u221e tracking control of unknown linear discrete-time systems"],"prefix":"10.1016","author":[{"given":"Yujie","family":"Su","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1077-980X","authenticated-orcid":false,"given":"Di","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Mi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.isatra.2026.09.025_bib0005","doi-asserted-by":"crossref","first-page":"892","DOI":"10.1109\/TIA.2018.2866560","article-title":"StructuredH\u221econtroller for an uncertain deregulated power system","volume":"55","author":"Rosaline","year":"2019","journal-title":"IEEE Trans Ind Appl"},{"issue":"3","key":"10.1016\/j.isatra.2026.09.025_bib0010","doi-asserted-by":"crossref","first-page":"164","DOI":"10.3390\/fractalfract6030164","article-title":"RobustH\u221econtrol of fractional-order switched systems with order0<\u03b1<1and uncertainty","volume":"6","author":"Li","year":"2022","journal-title":"Fractal Fract"},{"issue":"1","key":"10.1016\/j.isatra.2026.09.025_bib0015","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1109\/TCST.2025.3615663","article-title":"Robust H-Infinity control of feeding speed in coal seam drilling process with uncertain hardness","volume":"34","author":"Chen","year":"2026","journal-title":"IEEE Trans Control Syst Technol"},{"key":"10.1016\/j.isatra.2026.09.025_bib0020","series-title":"Proceedings of 35th IEEE conference on decision and control","first-page":"1595","article-title":"Robust and optimal control","volume":"vol. 2","author":"Doyle","year":"1996"},{"key":"10.1016\/j.isatra.2026.09.025_bib0025","series-title":"Robust andH\u221econtrol","author":"Chen","year":"2000"},{"issue":"11","key":"10.1016\/j.isatra.2026.09.025_bib0030","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-025-4614-9","article-title":"Zero-sum game control of unmanned aerial vehicle confrontation via reinforcement learning","volume":"68","author":"Li","year":"2025","journal-title":"Sci China Inf Sci"},{"issue":"9","key":"10.1016\/j.isatra.2026.09.025_bib0035","doi-asserted-by":"crossref","first-page":"5560","DOI":"10.1109\/TAC.2022.3220507","article-title":"Zero-sum games for finite-horizon semi-Markov processes under the probability criterion","volume":"68","author":"Huang","year":"2023","journal-title":"IEEE Trans Autom Control"},{"issue":"11","key":"10.1016\/j.isatra.2026.09.025_bib0040","doi-asserted-by":"crossref","first-page":"7523","DOI":"10.1109\/TAC.2025.3576039","article-title":"Convergence of heterogeneous learning dynamics in zero-sum stochastic games","volume":"70","author":"Arslantas","year":"2025","journal-title":"IEEE Trans Autom Control"},{"key":"10.1016\/j.isatra.2026.09.025_bib0045","series-title":"H\u221e optimal control and related minimax design problems: a dynamic game approach","author":"Ba\u015far","year":"2008"},{"issue":"4","key":"10.1016\/j.isatra.2026.09.025_bib0050","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1109\/TAC.1971.1099755","article-title":"An iterative technique for the computation of the steady state gains for the discrete optimal regulator","volume":"16","author":"Hewer","year":"1971","journal-title":"IEEE Trans Autom Control"},{"issue":"11","key":"10.1016\/j.isatra.2026.09.025_bib0055","doi-asserted-by":"crossref","first-page":"13344","DOI":"10.1109\/TPAMI.2023.3292075","article-title":"Transfer learning in deep reinforcement learning: a survey","volume":"45","author":"Zhu","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"10.1016\/j.isatra.2026.09.025_bib0060","doi-asserted-by":"crossref","first-page":"7449","DOI":"10.1109\/TNNLS.2024.3397704","article-title":"Eliminating primacy bias in online reinforcement learning by self-distillation","volume":"36","author":"Li","year":"2025","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10.1016\/j.isatra.2026.09.025_bib0065","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1016\/j.ins.2022.03.004","article-title":"Solution of the linear quadratic regulator problem of black box linear systems using reinforcement learning","volume":"595","author":"Perrusqu\u00eda","year":"2022","journal-title":"Inf Sci"},{"key":"10.1016\/j.isatra.2026.09.025_bib0070","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2025.112305","article-title":"Data-driven robust linear quadratic regulator: a minimax design using reinforcement learning","volume":"177","author":"Ma","year":"2025","journal-title":"Automatica"},{"issue":"11","key":"10.1016\/j.isatra.2026.09.025_bib0075","doi-asserted-by":"crossref","first-page":"7524","DOI":"10.1109\/TAC.2024.3386061","article-title":"Asynchronous distributed reinforcement learning for LQR control via zeroth-order block coordinate descent","volume":"69","author":"Jing","year":"2024","journal-title":"IEEE Trans Autom Control"},{"issue":"4","key":"10.1016\/j.isatra.2026.09.025_bib0080","doi-asserted-by":"crossref","first-page":"1995","DOI":"10.1109\/TCYB.2025.3540967","article-title":"Discounted inverse reinforcement learning for linear quadratic control","volume":"55","author":"Wu","year":"2025","journal-title":"IEEE Trans Cybern"},{"issue":"5","key":"10.1016\/j.isatra.2026.09.025_bib0085","doi-asserted-by":"crossref","first-page":"10249","DOI":"10.3934\/math.2023519","article-title":"Stochastic linear quadratic optimal tracking control for discrete-time systems with delays based on Q-learning algorithm","volume":"8","author":"Tan","year":"2023","journal-title":"AIMS Math"},{"key":"10.1016\/j.isatra.2026.09.025_bib0090","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2022.110761","article-title":"Linear quadratic tracking control of unknown systems: a two-phase reinforcement learning method","volume":"148","author":"Zhao","year":"2023","journal-title":"Automatica"},{"key":"10.1016\/j.isatra.2026.09.025_bib0095","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.automatica.2018.05.027","article-title":"Output feedback Q-learning for discrete-time linear zero-sum games with application to theH\u221econtrol","volume":"95","author":"Rizvi","year":"2018","journal-title":"Automatica"},{"key":"10.1016\/j.isatra.2026.09.025_bib0100","series-title":"Advances in neural networks \u2013 ISNN 2013, vol. 7952, Lecture Notes in Computer Science","first-page":"186","article-title":"Neural networkH\u221etracking control of nonlinear systems using GHJI method","author":"Liu","year":"2013"},{"issue":"10","key":"10.1016\/j.isatra.2026.09.025_bib0105","doi-asserted-by":"crossref","first-page":"2550","DOI":"10.1109\/TNNLS.2015.2441749","article-title":"H\u221e tracking control of completely unknown continuous-time systems via off-policy reinforcement learning","volume":"26","author":"Modares","year":"2015","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"2","key":"10.1016\/j.isatra.2026.09.025_bib0110","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1002\/acs.2830","article-title":"Output-feedbackH\u221equadratic tracking control of linear systems using reinforcement learning","volume":"33","author":"Moghadam","year":"2019","journal-title":"Int J Adapt Control Signal Process"},{"issue":"1","key":"10.1016\/j.isatra.2026.09.025_bib0115","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1109\/TSMCB.2010.2043839","article-title":"Reinforcement learning for partially observable dynamic processes: adaptive dynamic programming using measured output data","volume":"41","author":"Lewis","year":"2011","journal-title":"IEEE Trans Syst Man Cybern Part B Cybern"},{"key":"10.1016\/j.isatra.2026.09.025_bib0120","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.neucom.2018.05.111","article-title":"Linear quadratic tracking control of unknown discrete-time systems using value iteration algorithm","volume":"314","author":"Li","year":"2018","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.isatra.2026.09.025_bib0125","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1002\/rnc.4762","article-title":"H\u221e tracking control for linear discrete-time systems via reinforcement learning","volume":"30","author":"Liu","year":"2020","journal-title":"Int J Robust Nonlinear Control"},{"issue":"1","key":"10.1016\/j.isatra.2026.09.025_bib0130","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1109\/LCSYS.2020.3001241","article-title":"H\u221e tracking control for linear discrete-time systems: model-free Q-learning designs","volume":"5","author":"Yang","year":"2021","journal-title":"IEEE Control Syst Lett"},{"issue":"11","key":"10.1016\/j.isatra.2026.09.025_bib0135","doi-asserted-by":"crossref","first-page":"4109","DOI":"10.1109\/TSMC.2019.2957000","article-title":"Reinforcement Q-learning algorithm forH\u221etracking control of unknown discrete-time linear systems","volume":"50","author":"Peng","year":"2020","journal-title":"IEEE Trans Syst Man Cybern: Syst"},{"issue":"12","key":"10.1016\/j.isatra.2026.09.025_bib0140","doi-asserted-by":"crossref","first-page":"6805","DOI":"10.1002\/rnc.6169","article-title":"Output-feedback Q-learning for discrete-time linearH\u221etracking control: a Stackelberg game approach","volume":"32","author":"Ren","year":"2022","journal-title":"Int J Robust Nonlinear Control"},{"issue":"2","key":"10.1016\/j.isatra.2026.09.025_bib0145","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1109\/THFE.1966.232329","article-title":"Three models of preview control","volume":"7","author":"Sheridan","year":"1966","journal-title":"IEEE Trans Hum Factors Electron"},{"key":"10.1016\/j.isatra.2026.09.025_bib0150","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/j.isatra.2023.12.029","article-title":"Optimal preview pinning control of Boolean networks","volume":"146","author":"Wu","year":"2024","journal-title":"ISA Trans"},{"issue":"1","key":"10.1016\/j.isatra.2026.09.025_bib0155","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1049\/iet-cta.2016.0361","article-title":"Parameter-dependent preview control with robust tracking performance","volume":"11","author":"Li","year":"2017","journal-title":"IET Control Theory Appl"},{"issue":"3","key":"10.1016\/j.isatra.2026.09.025_bib0160","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1109\/JAS.2020.1003183","article-title":"Static-output-feedback based robust fuzzy wheelbase preview control for uncertain active suspensions with time delay and finite frequency constraint","volume":"8","author":"Li","year":"2020","journal-title":"IEEE\/CAA J Autom Sin"},{"key":"10.1016\/j.isatra.2026.09.025_bib0165","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.apm.2023.01.027","article-title":"Robust preview control of interconnected continuous-time systems with parametric uncertainties","volume":"118","author":"Xie","year":"2023","journal-title":"Appl Math Modell"},{"issue":"9","key":"10.1016\/j.isatra.2026.09.025_bib0170","doi-asserted-by":"crossref","first-page":"5061","DOI":"10.1002\/rnc.70455","article-title":"Reinforcement Q-learning forH\u221epreview control of unknown linear system","volume":"36","author":"Wang","year":"2026","journal-title":"Int J Robust Nonlinear Control"},{"issue":"4","key":"10.1016\/j.isatra.2026.09.025_bib0175","doi-asserted-by":"crossref","first-page":"1167","DOI":"10.1016\/j.automatica.2014.02.015","article-title":"Reinforcement Q-learning for optimal tracking control of linear discrete-time systems with unknown dynamics","volume":"50","author":"Kiumarsi","year":"2014","journal-title":"Automatica"},{"issue":"3","key":"10.1016\/j.isatra.2026.09.025_bib0180","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1109\/9.280789","article-title":"The discrete time Riccati equation related to theH\u221econtrol problem","volume":"39","author":"Stoorvogel","year":"1994","journal-title":"IEEE Trans Autom Control"},{"issue":"2","key":"10.1016\/j.isatra.2026.09.025_bib0185","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1016\/j.automatica.2008.08.017","article-title":"Adaptive optimal control for continuous-time linear systems based on policy iteration","volume":"45","author":"Vrabie","year":"2009","journal-title":"Automatica"},{"key":"10.1016\/j.isatra.2026.09.025_bib0190","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.automatica.2016.12.009","article-title":"H\u221e control of linear discrete-time systems: off-policy reinforcement learning","volume":"78","author":"Kiumarsi","year":"2017","journal-title":"Automatica"},{"key":"10.1016\/j.isatra.2026.09.025_bib0195","series-title":"Modern control systems","author":"Dorf","year":"2022"}],"container-title":["ISA Transactions"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0019057826004957?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0019057826004957?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T11:23:41Z","timestamp":1790249021000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0019057826004957"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":39,"alternative-id":["S0019057826004957"],"URL":"https:\/\/doi.org\/10.1016\/j.isatra.2026.09.025","relation":{},"ISSN":["0019-0578"],"issn-type":[{"value":"0019-0578","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Data-driven preview Q-learning for tracking control of unknown linear discrete-time systems","name":"articletitle","label":"Article Title"},{"value":"ISA Transactions","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.isatra.2026.09.025","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 International Society of Automation. Published by Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}