{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T16:03:29Z","timestamp":1777910609935,"version":"3.51.4"},"reference-count":44,"publisher":"SAGE Publications","issue":"15","license":[{"start":{"date-parts":[[2020,8,25]],"date-time":"2020-08-25T00:00:00Z","timestamp":1598313600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["Grant Nos. 61722306 and 61833007"],"award-info":[{"award-number":["Grant Nos. 61722306 and 61833007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Transactions of the Institute of Measurement and Control"],"published-print":{"date-parts":[[2020,11]]},"abstract":"<jats:p>In this paper, an online temporal differences (TD) learning approach is proposed to solve the robust control problem for discrete-time Markov jump linear systems (MJLS) subject to completely unknown transition probabilities (TP). The TD learning algorithm consists of two parts: policy evaluation and policy improvement. In the first part, by observing the mode jumping trajectories instead of solving a set of coupled algebraic Riccati equations, value functions are updated and approximate the TP related matrices. In the second part, new robust controllers can be obtained until value functions converge in the previous part. Moreover, the convergence of the value functions is proved by initializing a feasible control policy. Finally, two examples are presented to illustrate the effectiveness of the proposed approach by comparing with existing results.<\/jats:p>","DOI":"10.1177\/0142331220940208","type":"journal-article","created":{"date-parts":[[2020,8,25]],"date-time":"2020-08-25T09:31:40Z","timestamp":1598347900000},"page":"3043-3051","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":6,"title":["Robust control for Markov jump linear systems with unknown transition probabilities \u2013 an online temporal differences approach"],"prefix":"10.1177","volume":"42","author":[{"given":"Yaogang","family":"Chen","sequence":"first","affiliation":[{"name":"Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Institute of Automation, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8780-4762","authenticated-orcid":false,"given":"Jiwei","family":"Wen","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Institute of Automation, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6576-8174","authenticated-orcid":false,"given":"Xiaoli","family":"Luan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Institute of Automation, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Institute of Automation, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2020,8,25]]},"reference":[{"key":"bibr1-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264295"},{"key":"bibr2-0142331220940208","first-page":"2229","volume-title":"IEEE 57th Annual Conference on Decision and Control (CDC)","author":"Beirigo RL","year":"2018"},{"key":"bibr3-0142331220940208","volume-title":"Neuro-dynamic Programming","volume":"5","author":"Bertsekas DP","year":"1996"},{"key":"bibr4-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1080\/00207177508922037"},{"key":"bibr5-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.02.007"},{"key":"bibr6-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1177\/0142331218765610"},{"key":"bibr7-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1080\/00207178608933459"},{"key":"bibr8-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(01)00215-1"},{"key":"bibr9-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/9.478328"},{"key":"bibr10-0142331220940208","volume-title":"Discrete-time Markov jump linear systems","author":"Costa OLV","year":"2006"},{"key":"bibr11-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2006.875012"},{"key":"bibr12-0142331220940208","volume-title":"Continuous-time Markov jump linear systems","author":"do Valle Costa OL","year":"2012"},{"key":"bibr13-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/IranianCEE.2014.6999715"},{"key":"bibr14-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3602"},{"key":"bibr15-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.2807"},{"key":"bibr16-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.1610"},{"key":"bibr17-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2511306"},{"key":"bibr18-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2890046"},{"key":"bibr19-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2004.827145"},{"key":"bibr20-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.02.015"},{"key":"bibr21-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.03.032"},{"key":"bibr22-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2012.2229839"},{"key":"bibr23-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2008.928936"},{"key":"bibr24-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.10.056"},{"key":"bibr25-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-014-0576-4"},{"key":"bibr26-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1080\/002077299291912"},{"issue":"9","key":"bibr27-0142331220940208","first-page":"2101","volume":"28","author":"Shi P","year":"2016","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"bibr28-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2015.2442221"},{"key":"bibr29-0142331220940208","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton RS","year":"2018"},{"key":"bibr30-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2861470"},{"key":"bibr31-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2914160"},{"key":"bibr32-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.1760"},{"key":"bibr33-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2018.2878364"},{"key":"bibr34-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2992564"},{"key":"bibr35-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2831176"},{"key":"bibr36-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.06.018"},{"key":"bibr37-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.871880"},{"key":"bibr38-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.12.001"},{"key":"bibr39-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.1355"},{"key":"bibr40-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.02.002"},{"key":"bibr41-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.08.010"},{"key":"bibr42-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2531680"},{"key":"bibr43-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2018.12.038"},{"key":"bibr44-0142331220940208","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2013.04.003"}],"container-title":["Transactions of the Institute of Measurement and Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0142331220940208","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/0142331220940208","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0142331220940208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T15:01:51Z","timestamp":1777647711000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/0142331220940208"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,25]]},"references-count":44,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2020,11]]}},"alternative-id":["10.1177\/0142331220940208"],"URL":"https:\/\/doi.org\/10.1177\/0142331220940208","relation":{},"ISSN":["0142-3312","1477-0369"],"issn-type":[{"value":"0142-3312","type":"print"},{"value":"1477-0369","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,25]]}}}