{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,14]],"date-time":"2024-09-14T10:38:07Z","timestamp":1726310287792},"reference-count":30,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["Applied Mathematics and Computation"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1016\/j.amc.2021.126537","type":"journal-article","created":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T10:34:50Z","timestamp":1628678090000},"page":"126537","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":69,"special_numbering":"C","title":["Online reinforcement learning multiplayer non-zero sum games of continuous-time Markov jump linear systems"],"prefix":"10.1016","volume":"412","author":[{"given":"Xilin","family":"Xin","sequence":"first","affiliation":[]},{"given":"Yidong","family":"Tu","sequence":"additional","affiliation":[]},{"given":"Vladimir","family":"Stojanovic","sequence":"additional","affiliation":[]},{"given":"Hai","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Kaibo","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Shuping","family":"He","sequence":"additional","affiliation":[]},{"given":"Tianhong","family":"Pan","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"1\u20133","key":"10.1016\/j.amc.2021.126537_bib0001","first-page":"1021","article-title":"Analytical design of controllers in systems with random attributes","volume":"22","author":"Krasovskii","year":"1961","journal-title":"Autom. Remote Control"},{"issue":"1","key":"10.1016\/j.amc.2021.126537_bib0002","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1109\/TAC.1969.1099088","article-title":"Feedback control of a class of linear systems with jump parameters","volume":"14","author":"Sworder","year":"1969","journal-title":"IEEE Trans. Autom. Control"},{"issue":"5","key":"10.1016\/j.amc.2021.126537_bib0003","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1080\/00207177508922037","article-title":"Feedback control of a class of linear discrete systems with jump parameters and quadratic cost criteria","volume":"21","author":"Blair","year":"1975","journal-title":"Int. J. Control"},{"key":"10.1016\/j.amc.2021.126537_bib0004","unstructured":"W.M. Wonham, Random differential equations in control Theory, 1970."},{"issue":"2","key":"10.1016\/j.amc.2021.126537_bib0005","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1016\/j.automatica.2008.08.010","article-title":"Stability and stabilization of Markovian jump linear systems with partly unknown transition probabilities","volume":"45","author":"Zhang","year":"2009","journal-title":"Automatica"},{"issue":"2","key":"10.1016\/j.amc.2021.126537_bib0006","doi-asserted-by":"crossref","first-page":"947","DOI":"10.3182\/20130204-3-FR-2033.00186","article-title":"Sliding mode control of Markovian jump systems with partly unknown transition probabilities","volume":"46","author":"Zohrabi","year":"2013","journal-title":"IFAC Proc. Vol."},{"issue":"1\u20132","key":"10.1016\/j.amc.2021.126537_bib0007","first-page":"101","article-title":"Stability of discrete-time Markovian jump delay systems with delayed impulses and partly unknown transition","volume":"75","author":"Z.","year":"2014","journal-title":"Nonlinear Dyn."},{"key":"10.1016\/j.amc.2021.126537_bib0008","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1016\/j.neucom.2015.10.081","article-title":"Stochastic stability of nonlinear discrete-time Markovian jump systems with time-varying delay and partially unknown transition rates","volume":"175","author":"Hien","year":"2016","journal-title":"Neurocomputing."},{"key":"10.1016\/j.amc.2021.126537_bib0009","series-title":"2011\u00a0IEEE Int Symp Intell.","article-title":"Non-zero sum games: online learning solution of coupled Hamilton\u2013Jacobi and coupled Riccati equations","author":"Vamvoudakis","year":"2011"},{"issue":"2","key":"10.1016\/j.amc.2021.126537_bib0010","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"},{"issue":"2","key":"10.1016\/j.amc.2021.126537_bib0011","doi-asserted-by":"crossref","first-page":"2699","DOI":"10.1016\/j.automatica.2012.06.096","article-title":"Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics","volume":"48","author":"Jiang","year":"2012","journal-title":"Automatica"},{"key":"10.1016\/j.amc.2021.126537_bib0012","unstructured":"X. Zhang, H. Wang, V. Stojanovic, S. He, X. Luan, F. Liu, Asynchronous fault detection for interval type-2 fuzzy nonhomogeneous higher-level Markov jump systems with uncertain transition probabilities, IEEE Trans. Fuzzy Syst., 10.1109\/TFUZZ.2021.3086224"},{"key":"10.1016\/j.amc.2021.126537_bib0013","doi-asserted-by":"crossref","first-page":"109590","DOI":"10.1016\/j.automatica.2021.109590","article-title":"Finite-region asynchronous H\u221e control for 2D Markov jump systems","volume":"129","author":"Cheng","year":"2021","journal-title":"Automatica"},{"key":"10.1016\/j.amc.2021.126537_bib0014","unstructured":"Y. Tu, H. Fang, Y. Yin, S. He, Reinforcement learning-based nonlinear tracking control system design via LDI approach with application to trolley system, Neural Comput. Appl., 10.1007\/S00521-021-05909-8"},{"issue":"5","key":"10.1016\/j.amc.2021.126537_bib0015","doi-asserted-by":"crossref","first-page":"2002","DOI":"10.1109\/TNNLS.2020.2995708","article-title":"State estimation for persistent dwell-time switched coupled networks subject to round-robin protocol","volume":"32","author":"Shen","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn."},{"issue":"10","key":"10.1016\/j.amc.2021.126537_bib0016","doi-asserted-by":"crossref","first-page":"2335","DOI":"10.1109\/TFUZZ.2019.2935685","article-title":"Multi-objective fault-tolerant control for fuzzy switched systems with persistent dwell-time and its application in electric circuits","volume":"28","author":"Shen","year":"2020","journal-title":"IEEE Trans. Fuzzy Syst."},{"issue":"12","key":"10.1016\/j.amc.2021.126537_bib0017","doi-asserted-by":"crossref","first-page":"41224133","DOI":"10.1109\/TCYB.2016.2600753","article-title":"On group synchronization for interacting clusters of heterogeneous systems","volume":"47","author":"Qin","year":"2017","journal-title":"IEEE Trans. Cybern."},{"issue":"3","key":"10.1016\/j.amc.2021.126537_bib0018","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/MCAS.2009.933854","article-title":"Reinforcement learning and adaptive dynamic programming for feedback control","volume":"9","author":"Lewis","year":"2009","journal-title":"IEEE Circuits Syst. Mag."},{"issue":"7","key":"10.1016\/j.amc.2021.126537_bib0019","doi-asserted-by":"crossref","first-page":"3559","DOI":"10.1109\/TAC.2017.2660240","article-title":"Robust H\u221e group consensus for interacting clusters of integrator agents","volume":"62","author":"Qin","year":"2017","journal-title":"IEEE Trans. Autom Control"},{"issue":"3","key":"10.1016\/j.amc.2021.126537_bib0020","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1109\/TNNLS.2014.2316245","article-title":"Exponential synchronization of complex networks of linear systems and nonlinear oscillators: a unified analysis","volume":"26","author":"Qin","year":"2014","journal-title":"IEEE Trans. Neural Netw. Learn."},{"issue":"1","key":"10.1016\/j.amc.2021.126537_bib0021","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1109\/JSYST.2019.2891520","article-title":"An actor-critic deep reinforcement learning approach for transmission scheduling in cognitive internet of things systems","volume":"14","author":"Yang","year":"2019","journal-title":"IEEE Syst. J."},{"issue":"1","key":"10.1016\/j.amc.2021.126537_bib0022","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1109\/JSYST.2012.2208809","article-title":"Self-organized cooperation policy setting in P2P systems based on reinforcement learning","volume":"7","author":"Vakili","year":"2012","journal-title":"IEEE Syst. J."},{"issue":"4","key":"10.1016\/j.amc.2021.126537_bib0023","doi-asserted-by":"crossref","first-page":"1074","DOI":"10.1109\/JSYST.2013.2265187","article-title":"A novel system-centric intelligent adaptive control architecture for power system stabilizer based on adaptive neural networks","volume":"8","author":"Kamalasadan","year":"2013","journal-title":"IEEE Syst. J."},{"issue":"12","key":"10.1016\/j.amc.2021.126537_bib0024","first-page":"5281","article-title":"Extended dissipative control for singularly perturbed PDT switched systems and its application","volume":"67","author":"Wang","year":"2020","journal-title":"IEEE Trans. Circuits I"},{"key":"10.1016\/j.amc.2021.126537_bib0025","article-title":"H\u221e synchronization for fuzzy Markov jump chaotic systems with piecewise-constant transition probabilities subject to PDT switching rule","author":"Wang","year":"2020","journal-title":"IEEE Trans. Fuzzy Syst."},{"issue":"15","key":"10.1016\/j.amc.2021.126537_bib0026","doi-asserted-by":"crossref","first-page":"10921","DOI":"10.1016\/j.jfranklin.2020.08.037","article-title":"Network-based passive estimation for switched complex dynamical networks under persistent dwell-time with limited signals","volume":"357","author":"Wang","year":"2020","journal-title":"J. Frankl. Inst."},{"key":"10.1016\/j.amc.2021.126537_bib0027","series-title":"Continuous-Time Markov Jump Linear Systems","author":"Costa","year":"2012"},{"key":"10.1016\/j.amc.2021.126537_bib0028","series-title":"Jump Linear Systems in Automatic Control","author":"Mariton","year":"1990"},{"issue":"2","key":"10.1016\/j.amc.2021.126537_bib0029","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.amc.2021.126537_bib0030","series-title":"Dynamic Noncooperative Game Theory","author":"Basar","year":"1998"}],"container-title":["Applied Mathematics and Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0096300321006214?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0096300321006214?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T04:55:14Z","timestamp":1672808114000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0096300321006214"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1]]},"references-count":30,"alternative-id":["S0096300321006214"],"URL":"https:\/\/doi.org\/10.1016\/j.amc.2021.126537","relation":{},"ISSN":["0096-3003"],"issn-type":[{"value":"0096-3003","type":"print"}],"subject":[],"published":{"date-parts":[[2022,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Online reinforcement learning multiplayer non-zero sum games of continuous-time Markov jump linear systems","name":"articletitle","label":"Article Title"},{"value":"Applied Mathematics and Computation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.amc.2021.126537","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2021 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"126537"}}
