{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T04:36:38Z","timestamp":1728534998189},"reference-count":28,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1016\/j.ins.2024.121212","type":"journal-article","created":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T18:59:22Z","timestamp":1721847562000},"page":"121212","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Q-learning based tracking control with novel finite-horizon performance index"],"prefix":"10.1016","volume":"681","author":[{"given":"Wei","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoxu","family":"Mu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoxian","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.ins.2024.121212_br0010","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."},{"issue":"11","key":"10.1016\/j.ins.2024.121212_br0020","doi-asserted-by":"crossref","first-page":"4056","DOI":"10.1109\/TSMC.2019.2895692","article-title":"ADP-based robust tracking control for a class of nonlinear systems with unmatched uncertainties","volume":"50","author":"Mu","year":"2020","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"10.1016\/j.ins.2024.121212_br0030","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1016\/j.ins.2023.01.031","article-title":"Optimal output tracking of Boolean control networks","volume":"626","author":"Pan","year":"2023","journal-title":"Inf. Sci."},{"year":"2018","series-title":"Reinforcement Learning: An Introduction","author":"Sutton","key":"10.1016\/j.ins.2024.121212_br0040"},{"issue":"3\u20134","key":"10.1016\/j.ins.2024.121212_br0050","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"issue":"3","key":"10.1016\/j.ins.2024.121212_br0060","first-page":"1094","article-title":"Based on Q-learning optimal tracking control schemes for linear It\u00f4 stochastic systems with Markovian jumps","volume":"70","author":"Li","year":"2023","journal-title":"IEEE Trans. Circuits Syst. II, Express Briefs"},{"issue":"4","key":"10.1016\/j.ins.2024.121212_br0070","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"},{"key":"10.1016\/j.ins.2024.121212_br0080","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2019.105593","article-title":"An ADDHP-based Q-learning algorithm for optimal tracking control of linear discrete-time systems with unknown dynamics","volume":"82","author":"Mu","year":"2019","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.ins.2024.121212_br0090","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.isatra.2021.06.007","article-title":"Novel data-driven two-dimensional Q-learning for optimal tracking control of batch process with unknown dynamics","volume":"125","author":"Wen","year":"2022","journal-title":"ISA Trans."},{"issue":"12","key":"10.1016\/j.ins.2024.121212_br0100","doi-asserted-by":"crossref","first-page":"7523","DOI":"10.1109\/TNNLS.2021.3085358","article-title":"Reinforcement learning based optimal tracking control under unmeasurable disturbances with application to HVAC systems","volume":"33","author":"Rizvi","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"11","key":"10.1016\/j.ins.2024.121212_br0110","doi-asserted-by":"crossref","first-page":"7770","DOI":"10.1109\/TII.2022.3151797","article-title":"Reinforcement learning and optimal setpoint tracking control of linear systems with external disturbances","volume":"18","author":"Zhao","year":"2022","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.ins.2024.121212_br0120","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.jprocont.2022.03.006","article-title":"Novel two-dimensional off-policy Q-learning method for output feedback optimal tracking control of batch process with unknown dynamics","volume":"113","author":"Shi","year":"2022","journal-title":"J. Process Control"},{"issue":"2","key":"10.1016\/j.ins.2024.121212_br0130","doi-asserted-by":"crossref","first-page":"1032","DOI":"10.1109\/TCNS.2022.3213718","article-title":"Two-dimensional model-free optimal tracking control for batch processes with packet loss","volume":"10","author":"Shi","year":"2023","journal-title":"IEEE Trans. Control Netw. Syst."},{"key":"10.1016\/j.ins.2024.121212_br0140","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1016\/j.ins.2023.01.030","article-title":"Discounted linear Q-learning control with novel tracking cost and its stability","volume":"626","author":"Wang","year":"2023","journal-title":"Inf. Sci."},{"issue":"10","key":"10.1016\/j.ins.2024.121212_br0150","doi-asserted-by":"crossref","first-page":"2134","DOI":"10.1109\/TNNLS.2016.2585520","article-title":"Model-free optimal tracking control via critic-only Q-learning","volume":"27","author":"Luo","year":"2016","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"1","key":"10.1016\/j.ins.2024.121212_br0160","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1109\/TNNLS.2022.3178746","article-title":"Model-free optimal tracking control of nonlinear input-affine discrete-time systems via an iterative deterministic Q-learning algorithm","volume":"35","author":"Song","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"1","key":"10.1016\/j.ins.2024.121212_br0170","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1002\/rnc.5263","article-title":"Robust optimal tracking control for multiplayer systems by off-policy Q-learning approach","volume":"31","author":"Li","year":"2021","journal-title":"Int. J. Robust Nonlinear"},{"issue":"11","key":"10.1016\/j.ins.2024.121212_br0180","doi-asserted-by":"crossref","first-page":"4109","DOI":"10.1109\/TSMC.2019.2957000","article-title":"Reinforcement Q-learning algorithm for H\u221e tracking control of unknown discrete-time linear systems","volume":"50","author":"Peng","year":"2020","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"year":"2018","series-title":"Self-Learning Optimal Control of Nonlinear Systems","author":"Wei","key":"10.1016\/j.ins.2024.121212_br0190"},{"issue":"1","key":"10.1016\/j.ins.2024.121212_br0200","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.neucom.2011.03.058","article-title":"Finite-horizon neuro-optimal tracking control for a class of discrete-time nonlinear systems using adaptive dynamic programming approach","volume":"78","author":"Wang","year":"2012","journal-title":"Neurocomputing"},{"key":"10.1016\/j.ins.2024.121212_br0210","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1016\/j.neucom.2013.09.006","article-title":"Fixed-final-time optimal tracking control of input-affine nonlinear systems","volume":"129","author":"Heydari","year":"2014","journal-title":"Neurocomputing"},{"issue":"12","key":"10.1016\/j.ins.2024.121212_br0220","doi-asserted-by":"crossref","first-page":"1791","DOI":"10.1049\/iet-cta.2014.1325","article-title":"Finite horizon optimal tracking control of partially unknown linear continuous-time systems using policy iteration","volume":"9","author":"Li","year":"2015","journal-title":"IET Control Theory Appl."},{"key":"10.1016\/j.ins.2024.121212_br0230","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1016\/j.neucom.2019.05.026","article-title":"Data-driven finite-horizon optimal tracking control scheme for completely unknown discrete-time nonlinear systems","volume":"356","author":"Song","year":"2019","journal-title":"Neurocomputing"},{"issue":"4","key":"10.1016\/j.ins.2024.121212_br0240","doi-asserted-by":"crossref","first-page":"1200","DOI":"10.1109\/TNNLS.2017.2669099","article-title":"Finite-horizon H\u221e tracking control for unknown nonlinear systems with saturating actuators","volume":"29","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"11","key":"10.1016\/j.ins.2024.121212_br0250","doi-asserted-by":"crossref","first-page":"5514","DOI":"10.1109\/TAC.2021.3056398","article-title":"An iterative data-driven linear quadratic method to solve nonlinear discrete-time tracking problems","volume":"66","author":"Possieri","year":"2021","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.ins.2024.121212_br0260","article-title":"Model-free finite-horizon optimal tracking control of discrete-time linear systems","volume":"433","author":"Wang","year":"2022","journal-title":"Appl. Math. Comput."},{"key":"10.1016\/j.ins.2024.121212_br0270","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2021.109687","article-title":"A novel adaptive dynamic programming based on tracking error for nonlinear discrete-time systems","volume":"129","author":"Li","year":"2021","journal-title":"Automatica"},{"year":"2006","series-title":"Optimal State Estimation: Kalman, H Infinity, and Nonlinear Approaches","author":"Simon","key":"10.1016\/j.ins.2024.121212_br0280"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025524011265?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025524011265?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T21:08:48Z","timestamp":1728508128000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025524011265"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":28,"alternative-id":["S0020025524011265"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2024.121212","relation":{},"ISSN":["0020-0255"],"issn-type":[{"type":"print","value":"0020-0255"}],"subject":[],"published":{"date-parts":[[2024,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Q-learning based tracking control with novel finite-horizon performance index","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2024.121212","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"121212"}}