{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:31:30Z","timestamp":1783542690376,"version":"3.55.0"},"reference-count":31,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2024YFE0208100"],"award-info":[{"award-number":["2024YFE0208100"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2024MF045"],"award-info":[{"award-number":["ZR2024MF045"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472262"],"award-info":[{"award-number":["62472262"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62503289"],"award-info":[{"award-number":["62503289"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62273213"],"award-info":[{"award-number":["62273213"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A20325"],"award-info":[{"award-number":["U23A20325"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Systems & Control Letters"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.sysconle.2026.106505","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T10:27:32Z","timestamp":1781692052000},"page":"106505","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Output feedback Q-learning for decentralized finite-horizon nonzero-sum games with asymmetric information"],"prefix":"10.1016","volume":"215","author":[{"given":"Qiyan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaorong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0024-8893","authenticated-orcid":false,"given":"Hongxia","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.sysconle.2026.106505_b1","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1016\/j.energy.2015.01.027","article-title":"Demand side management in a smart grid with multiple electricity suppliers","volume":"81","author":"Jalali","year":"2015","journal-title":"Energy"},{"issue":"4\u20135","key":"10.1016\/j.sysconle.2026.106505_b2","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1016\/0191-2615(84)90013-4","article-title":"Game theory and transportation systems modelling","volume":"18","author":"Fisk","year":"1984","journal-title":"Transp. Res. Part B: Methodol."},{"key":"10.1016\/j.sysconle.2026.106505_b3","series-title":"Dynamic noncooperative game theory","author":"Ba\u015far","year":"1998"},{"issue":"5","key":"10.1016\/j.sysconle.2026.106505_b4","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1109\/JAS.2022.105506","article-title":"Cooperative and competitive multi-agent systems: From optimization to games","volume":"9","author":"Wang","year":"2022","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"10.1016\/j.sysconle.2026.106505_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126276","article-title":"Fuzzy logic nonzero-sum game-based distributed approximated optimal control of modular robot manipulators with human-robot collaboration","volume":"543","author":"An","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.sysconle.2026.106505_b6","volume":"vol. 1","author":"Haurie","year":"2012"},{"issue":"2","key":"10.1016\/j.sysconle.2026.106505_b7","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1007\/s11768-012-0038-6","article-title":"Infinite horizon H-two\/h-infinity control for descriptor systems: Nash game approach","volume":"10","author":"Yan","year":"2012","journal-title":"J. Control Theory Appl."},{"key":"10.1016\/j.sysconle.2026.106505_b8","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1051\/cocv\/2021078","article-title":"Mean-field linear-quadratic stochastic differential games in an infinite horizon","volume":"27","author":"Li","year":"2021","journal-title":"ESAIM Control Optim. Calc. Var."},{"issue":"3","key":"10.1016\/j.sysconle.2026.106505_b9","doi-asserted-by":"crossref","first-page":"1417","DOI":"10.1137\/23M1579960","article-title":"Feedback and open-loop Nash equilibria for LQ infinite-horizon discrete-time dynamic games","volume":"62","author":"Monti","year":"2024","journal-title":"SIAM J. Control Optim."},{"issue":"2","key":"10.1016\/j.sysconle.2026.106505_b10","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1109\/TAC.2016.2555879","article-title":"Feedback Nash equilibria in linear-quadratic difference games with constraints","volume":"62","author":"Reddy","year":"2016","journal-title":"IEEE Trans. Autom. Control"},{"issue":"3","key":"10.1016\/j.sysconle.2026.106505_b11","first-page":"1024","article-title":"Feedback nash equilibrium with packet dropouts in networked control systems","volume":"70","author":"Sun","year":"2022","journal-title":"IEEE Trans. Circuits Syst. II: Express Briefs"},{"issue":"2\u20134","key":"10.1016\/j.sysconle.2026.106505_b12","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1504\/IJVAS.2010.035795","article-title":"Optimal vehicle stability controller based on Nash strategy for differential LQ games","volume":"8","author":"Tamaddoni","year":"2010","journal-title":"Int. J. Veh. Auton. Syst."},{"issue":"2","key":"10.1016\/j.sysconle.2026.106505_b13","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1109\/TCNS.2015.2428332","article-title":"Nash game-based distributed control design for balancing traffic density over freeway networks","volume":"3","author":"Pisarski","year":"2015","journal-title":"IEEE Trans. Control. Netw. Syst."},{"issue":"1","key":"10.1016\/j.sysconle.2026.106505_b14","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.arcontrol.2014.03.007","article-title":"Decentralized control: Status and outlook","volume":"38","author":"Bakule","year":"2014","journal-title":"Annu. Rev. Control."},{"issue":"8","key":"10.1016\/j.sysconle.2026.106505_b15","doi-asserted-by":"crossref","first-page":"3920","DOI":"10.1109\/TAC.2021.3109520","article-title":"Decentralized control of multiagent systems using local density feedback","volume":"67","author":"Biswal","year":"2021","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.sysconle.2026.106505_b16","doi-asserted-by":"crossref","DOI":"10.1109\/TCSI.2024.3401693","article-title":"Distributed dual-terminal adaptive triggered consensus tracking of descriptor multi-agent systems against asynchronous DoS attacks with Markov switching topologies","author":"Zhu","year":"2024","journal-title":"IEEE Trans. Circuits Syst. I. Regul. Pap."},{"issue":"1","key":"10.1016\/j.sysconle.2026.106505_b17","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1002\/oca.3062","article-title":"Differential privacy optimal control with asymmetric information structure","volume":"45","author":"Zhang","year":"2024","journal-title":"Optim. Control. Appl. Methods"},{"issue":"4","key":"10.1016\/j.sysconle.2026.106505_b18","doi-asserted-by":"crossref","first-page":"2076","DOI":"10.1109\/TAC.2021.3073069","article-title":"Decentralized control for networked control systems with asymmetric information","volume":"67","author":"Liang","year":"2021","journal-title":"IEEE Trans. Autom. Control"},{"issue":"7","key":"10.1016\/j.sysconle.2026.106505_b19","doi-asserted-by":"crossref","first-page":"1644","DOI":"10.1109\/TAC.2013.2239000","article-title":"Decentralized stochastic control with partial history sharing: A common information approach","volume":"58","author":"Nayyar","year":"2013","journal-title":"IEEE Trans. Autom. Control"},{"issue":"9","key":"10.1016\/j.sysconle.2026.106505_b20","doi-asserted-by":"crossref","first-page":"2377","DOI":"10.1109\/TAC.2013.2251807","article-title":"Optimal decentralized control of coupled subsystems with control sharing","volume":"58","author":"Mahajan","year":"2013","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.sysconle.2026.106505_b21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11432-018-9617-0","article-title":"Decentralized control for linear systems with multiple input channels","volume":"62","author":"Xu","year":"2019","journal-title":"Sci. China Inf. Sci."},{"key":"10.1016\/j.sysconle.2026.106505_b22","series-title":"Decentralized control of linear systems with private input and measurement information","author":"Xu","year":"2023"},{"issue":"3","key":"10.1016\/j.sysconle.2026.106505_b23","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1016\/j.automatica.2006.09.019","article-title":"Model-free Q-learning designs for linear discrete-time zero-sum games with application to H-infinity control","volume":"43","author":"Al-Tamimi","year":"2007","journal-title":"Automatica"},{"issue":"Nov","key":"10.1016\/j.sysconle.2026.106505_b24","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"Hu","year":"2003","journal-title":"J. Mach. Learn. Res."},{"issue":"9","key":"10.1016\/j.sysconle.2026.106505_b25","doi-asserted-by":"crossref","first-page":"9170","DOI":"10.1109\/TCYB.2021.3052832","article-title":"Q-learning for feedback Nash strategy of finite-horizon nonzero-sum difference games","volume":"52","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Cybern."},{"issue":"1","key":"10.1016\/j.sysconle.2026.106505_b26","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":"2010","journal-title":"IEEE Trans. Syst. Man Cybern. B"},{"issue":"7","key":"10.1016\/j.sysconle.2026.106505_b27","doi-asserted-by":"crossref","first-page":"3274","DOI":"10.1109\/TNNLS.2020.3010304","article-title":"Output feedback Q-learning for linear-quadratic discrete-time finite-horizon control problems","volume":"32","author":"Calafiore","year":"2020","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.sysconle.2026.106505_b28","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.neucom.2023.01.050","article-title":"Output feedback Q-learning for discrete-time finite-horizon zero-sum games with application to the H-infinity control","volume":"529","author":"Liu","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.sysconle.2026.106505_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2021.110076","article-title":"Off-policy Q-learning: Solving Nash equilibrium of multi-player games with network-induced delay and unmeasured state","volume":"136","author":"Li","year":"2022","journal-title":"Automatica"},{"key":"10.1016\/j.sysconle.2026.106505_b30","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-025-4848-2","article-title":"Distributed optimization algorithm with superlinear convergence rate","volume":"69","author":"Xu","year":"2026","journal-title":"Sci. China Inf. Sci."},{"key":"10.1016\/j.sysconle.2026.106505_b31","doi-asserted-by":"crossref","DOI":"10.1109\/TSMC.2025.3600349","article-title":"Model-free Q-learning for output feedback Nash strategy of decentralized nonzero-sum games","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Syst. Man Cybern.: Syst."}],"container-title":["Systems & Control Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167691126001659?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167691126001659?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:12:53Z","timestamp":1783541573000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167691126001659"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":31,"alternative-id":["S0167691126001659"],"URL":"https:\/\/doi.org\/10.1016\/j.sysconle.2026.106505","relation":{},"ISSN":["0167-6911"],"issn-type":[{"value":"0167-6911","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Output feedback Q-learning for decentralized finite-horizon nonzero-sum games with asymmetric information","name":"articletitle","label":"Article Title"},{"value":"Systems & Control Letters","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.sysconle.2026.106505","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"106505"}}