{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:16:20Z","timestamp":1785604580109,"version":"3.56.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T00:00:00Z","timestamp":1711497600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T00:00:00Z","timestamp":1711497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s11432-023-3982-y","type":"journal-article","created":{"date-parts":[[2024,4,4]],"date-time":"2024-04-04T08:02:26Z","timestamp":1712217746000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":63,"title":["Online Pareto optimal control of mean-field stochastic multi-player systems using policy iteration"],"prefix":"10.1007","volume":"67","author":[{"given":"Xiushan","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanshuang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongya","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,27]]},"reference":[{"key":"3982_CR1","doi-asserted-by":"publisher","first-page":"5169","DOI":"10.1109\/TII.2019.2955966","volume":"16","author":"C Mu","year":"2020","unstructured":"Mu C, Wang K, Ni Z, et al. Cooperative differential game-based optimal control and its application to power systems. IEEE Trans Ind Inf, 2020, 16: 5169\u20135179","journal-title":"IEEE Trans Ind Inf"},{"key":"3982_CR2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511805127","volume-title":"Differential Games in Economics and Management Science","author":"E J Dockner","year":"2000","unstructured":"Dockner E J, Jorgensen S, Long N V, et al. Differential Games in Economics and Management Science. Cambridge: Cambridge University Press, 2000"},{"key":"3982_CR3","doi-asserted-by":"publisher","first-page":"7574","DOI":"10.1109\/TSMC.2022.3160158","volume":"52","author":"Q Sun","year":"2022","unstructured":"Sun Q, Wang X, Yang G, et al. Optimal constraint following for fuzzy mechanical systems based on a time-varying \u03b2-measure and cooperative game theory. IEEE Trans Syst Man Cybern Syst, 2022, 52: 7574\u20137587","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"3982_CR4","doi-asserted-by":"publisher","first-page":"2453","DOI":"10.1016\/j.automatica.2008.01.022","volume":"44","author":"J Engwerda","year":"2008","unstructured":"Engwerda J. The regular convex cooperative linear quadratic control problem. Automatica, 2008, 44: 2453\u20132457","journal-title":"Automatica"},{"key":"3982_CR5","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1016\/j.automatica.2018.04.044","volume":"94","author":"Y Lin","year":"2018","unstructured":"Lin Y, Jiang X, Zhang W. Necessary and sufficient conditions for Pareto optimality of the stochastic systems in finite horizon. Automatica, 2018, 94: 341\u2013348","journal-title":"Automatica"},{"key":"3982_CR6","doi-asserted-by":"publisher","first-page":"11805","DOI":"10.1109\/TCYB.2021.3070352","volume":"52","author":"W Zhang","year":"2022","unstructured":"Zhang W, Peng C. Indefinite mean-field stochastic cooperative linear-quadratic dynamic difference game with its application to the network security model. IEEE Trans Cybern, 2022, 52: 11805\u201311818","journal-title":"IEEE Trans Cybern"},{"key":"3982_CR7","doi-asserted-by":"publisher","first-page":"6963","DOI":"10.1109\/TCYB.2022.3179605","volume":"53","author":"X Jiang","year":"2023","unstructured":"Jiang X, Su S F, Zhao D. Pareto optimal strategy under H\u221e constraint for the mean-field stochastic systems in infinite horizon. IEEE Trans Cybern, 2023, 53: 6963\u20136976","journal-title":"IEEE Trans Cybern"},{"key":"3982_CR8","doi-asserted-by":"publisher","first-page":"3461","DOI":"10.1109\/TAC.2018.2881141","volume":"64","author":"Q Qi","year":"2019","unstructured":"Qi Q, Zhang H, Wu Z. Stabilization control for linear continuous-time mean-field systems. IEEE Trans Autom Control, 2019, 64: 3461\u20133468","journal-title":"IEEE Trans Autom Control"},{"key":"3982_CR9","doi-asserted-by":"publisher","first-page":"6423","DOI":"10.1109\/TAC.2023.3238849","volume":"68","author":"T Zhang","year":"2023","unstructured":"Zhang T, Deng F, Shi P. Nonfragile finite-time stabilization for discrete mean-field stochastic systems. IEEE Trans Autom Control, 2023, 68: 6423\u20136430","journal-title":"IEEE Trans Autom Control"},{"key":"3982_CR10","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.automatica.2018.03.017","volume":"92","author":"Y Lin","year":"2018","unstructured":"Lin Y, Zhang T, Zhang W. Pareto-based guaranteed cost control of the uncertain mean-field stochastic systems in infinite horizon. Automatica, 2018, 92: 197\u2013209","journal-title":"Automatica"},{"key":"3982_CR11","doi-asserted-by":"publisher","first-page":"5532","DOI":"10.1016\/j.jfranklin.2021.05.013","volume":"358","author":"Y Lin","year":"2021","unstructured":"Lin Y, Zhang W. Pareto efficiency in the infinite horizon mean-field type cooperative stochastic differential game. J Franklin Inst, 2021, 358: 5532\u20135551","journal-title":"J Franklin Inst"},{"key":"3982_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2018.04.018","volume":"312","author":"T Wang","year":"2018","unstructured":"Wang T, Zhang H, Luo Y. Stochastic linear quadratic optimal control for model-free discrete-time systems based on Q-learning algorithm. Neurocomputing, 2018, 312: 1\u20138","journal-title":"Neurocomputing"},{"key":"3982_CR13","doi-asserted-by":"publisher","first-page":"5522","DOI":"10.1109\/TNNLS.2020.2969215","volume":"31","author":"M Liu","year":"2020","unstructured":"Liu M, Wan Y, Lewis F L, et al. Adaptive optimal control for stochastic multiplayer differential games using on-policy and off-policy reinforcement learning. IEEE Trans Neural Netw Learn Syst, 2020, 31: 5522\u20135533","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"3982_CR14","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.sysconle.2018.03.001","volume":"115","author":"T Bian","year":"2018","unstructured":"Bian T, Jiang Z P. Stochastic and adaptive optimal control of uncertain interconnected systems: a data-driven approach. Syst Control Lett, 2018, 115: 48\u201354","journal-title":"Syst Control Lett"},{"key":"3982_CR15","volume-title":"Dynamic Programming and Markov Processes","author":"R A Howard","year":"1960","unstructured":"Howard R A. Dynamic Programming and Markov Processes. Cambridge: MIT Press, 1960"},{"key":"3982_CR16","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TSMC.1983.6313077","volume":"SMC-13","author":"A G Barto","year":"1983","unstructured":"Barto A G, Sutton R S, Anderson C W. Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Trans Syst Man Cybern, 1983, SMC-13: 834\u2013846","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"3982_CR17","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1016\/j.automatica.2008.08.017","volume":"45","author":"D Vrabie","year":"2009","unstructured":"Vrabie D, Pastravanu O, Abu-Khalaf M, et al. Adaptive optimal control for continuous-time linear systems based on policy iteration. Automatica, 2009, 45: 477\u2013484","journal-title":"Automatica"},{"key":"3982_CR18","doi-asserted-by":"publisher","first-page":"2042","DOI":"10.1109\/TNNLS.2017.2773458","volume":"29","author":"B Kiumarsi","year":"2018","unstructured":"Kiumarsi B, Vamvoudakis K G, Modares H, et al. Optimal and autonomous control using reinforcement learning: a survey. IEEE Trans Neural Netw Learn Syst, 2018, 29: 2042\u20132062","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"3982_CR19","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/TAC.2021.3085510","volume":"67","author":"B Pang","year":"2022","unstructured":"Pang B, Bian T, Jiang Z P. Robust policy iteration for continuous-time linear quadratic regulation. IEEE Trans Autom Control, 2022, 67: 504\u2013511","journal-title":"IEEE Trans Autom Control"},{"key":"3982_CR20","doi-asserted-by":"publisher","first-page":"5009","DOI":"10.1109\/TAC.2022.3181248","volume":"67","author":"N Li","year":"2022","unstructured":"Li N, Li X, Peng J, et al. Stochastic linear quadratic optimal control problem: a reinforcement learning method. IEEE Trans Autom Control, 2022, 67: 5009\u20135016","journal-title":"IEEE Trans Autom Control"},{"key":"3982_CR21","doi-asserted-by":"publisher","first-page":"2383","DOI":"10.1109\/TAC.2022.3172250","volume":"68","author":"B Pang","year":"2022","unstructured":"Pang B, Jiang Z P. Reinforcement learning for adaptive optimal stationary control of linear stochastic systems. IEEE Trans Autom Control, 2022, 68: 2383\u20132390","journal-title":"IEEE Trans Autom Control"},{"key":"3982_CR22","doi-asserted-by":"publisher","first-page":"3009","DOI":"10.1109\/TAC.2012.2197074","volume":"57","author":"W H Zhang","year":"2012","unstructured":"Zhang W H, Chen B S. \u210c-representation and applications to generalized Lyapunov equations and linear stochastic systems. IEEE Trans Autom Control, 2012, 57: 3009\u20133022","journal-title":"IEEE Trans Autom Control"},{"key":"3982_CR23","volume-title":"Cooperative and Noncooperative Many Player Differential Games","author":"G Leitmann","year":"1974","unstructured":"Leitmann G. Cooperative and Noncooperative Many Player Differential Games. Berlin: Springer-Verlag, 1974"},{"key":"3982_CR24","volume-title":"LQ Dynamic Optimization and Differential Games","author":"J C Engwerda","year":"2005","unstructured":"Engwerda J C. LQ Dynamic Optimization and Differential Games. Chichester: Wiley, 2005"},{"key":"3982_CR25","doi-asserted-by":"publisher","first-page":"109267","DOI":"10.1016\/j.automatica.2020.109267","volume":"122","author":"N Li","year":"2020","unstructured":"Li N, Li X, Yu Z. Indefinite mean-field type linear-quadratic stochastic optimal control problems. Automatica, 2020, 122: 109267","journal-title":"Automatica"},{"key":"3982_CR26","volume-title":"Stochastic Differential Equations: An Introduction with Applications","author":"B \u00d8ksendal","year":"2013","unstructured":"\u00d8ksendal B. Stochastic Differential Equations: An Introduction with Applications. New York: Springer, 2013"},{"key":"3982_CR27","doi-asserted-by":"publisher","first-page":"8366","DOI":"10.1109\/TWC.2020.3021907","volume":"19","author":"R A Banez","year":"2020","unstructured":"Banez R A, Tembine H, Li L, et al. Mean-field-type game-based computation offloading in multi-access edge computing networks. IEEE Trans Wireless Commun, 2020, 19: 8366\u20138381","journal-title":"IEEE Trans Wireless Commun"},{"key":"3982_CR28","doi-asserted-by":"publisher","first-page":"1131","DOI":"10.1109\/9.863597","volume":"45","author":"M A Rami","year":"2000","unstructured":"Rami M A, Xun Yu, Zhou M A. Linear matrix inequalities, Riccati equations, and indefinite stochastic linear quadratic controls. IEEE Trans Autom Control, 2000, 45: 1131\u20131143","journal-title":"IEEE Trans Autom Control"},{"key":"3982_CR29","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1109\/TSMC.2018.2882590","volume":"51","author":"Z Hu","year":"2021","unstructured":"Hu Z, Shi P, Zhang J, et al. Control of discrete-time stochastic systems with packet loss by event-triggered approach. IEEE Trans Syst Man Cybern Syst, 2021, 51: 755\u2013764","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"3982_CR30","doi-asserted-by":"publisher","first-page":"9316","DOI":"10.1109\/TCYB.2021.3069423","volume":"52","author":"W Qi","year":"2022","unstructured":"Qi W, Yang X, Park J H, et al. Fuzzy SMC for quantized nonlinear stochastic switching systems with semi-Markovian process and application. IEEE Trans Cybern, 2022, 52: 9316\u20139325","journal-title":"IEEE Trans Cybern"},{"key":"3982_CR31","doi-asserted-by":"publisher","first-page":"209204","DOI":"10.1007\/s11432-019-9857-5","volume":"64","author":"X S Jiang","year":"2021","unstructured":"Jiang X S, Tian S P, Zhang W H. pth moment exponential stability of general nonlinear discrete-time stochastic systems. Sci China Inf Sci, 2021, 64: 209204","journal-title":"Sci China Inf Sci"},{"key":"3982_CR32","doi-asserted-by":"publisher","first-page":"182202","DOI":"10.1007\/s11432-022-3690-y","volume":"66","author":"T L Zhang","year":"2023","unstructured":"Zhang T L, Xu S Y, Zhang W H. Predefined-time stabilization for nonlinear stochastic It\u00f4 systems. Sci China Inf Sci, 2023, 66: 182202","journal-title":"Sci China Inf Sci"},{"key":"3982_CR33","doi-asserted-by":"publisher","first-page":"1934","DOI":"10.1109\/TCYB.2023.3300120","volume":"54","author":"W Qi","year":"2024","unstructured":"Qi W, Zhang N, Zong G, et al. Asynchronous sliding-mode control for discrete-time networked hidden stochastic jump systems with cyber attacks. IEEE Trans Cybern, 2024, 54: 1934\u20131946","journal-title":"IEEE Trans Cybern"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-023-3982-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-023-3982-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-023-3982-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T19:44:29Z","timestamp":1747770269000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-023-3982-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,27]]},"references-count":33,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["3982"],"URL":"https:\/\/doi.org\/10.1007\/s11432-023-3982-y","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,27]]},"assertion":[{"value":"31 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 January 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"140202"}}