{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T13:03:37Z","timestamp":1784379817502,"version":"3.55.0"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100011248","name":"State Key Laboratory of Synthetical Automation for Process Industries","doi-asserted-by":"publisher","award":["2013ZCX01"],"award-info":[{"award-number":["2013ZCX01"]}],"id":[{"id":"10.13039\/501100011248","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62273079"],"award-info":[{"award-number":["62273079"]}],"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":["625B2040"],"award-info":[{"award-number":["625B2040"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Fuzzy Sets and Systems"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.fss.2026.109947","type":"journal-article","created":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T06:47:20Z","timestamp":1779518840000},"page":"109947","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Stabilizing three-phase reinforcement learning for optimal output consensus in stochastic Takagi-Sugeno fuzzy multi-agent systems"],"prefix":"10.1016","volume":"542","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6756-5671","authenticated-orcid":false,"given":"Zihan","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8814-146X","authenticated-orcid":false,"given":"Dongdong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9389-4741","authenticated-orcid":false,"given":"Jiuxiang","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.fss.2026.109947_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.jfranklin.2025.108270","article-title":"Fuzzy observer-based adaptive fault tolerant control for uncertain underactuated nonlinear systems under TS fuzzy model with unmeasured premise variables","volume":"363","author":"Dong","year":"2026","journal-title":"J. Franklin Inst."},{"key":"10.1016\/j.fss.2026.109947_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.fss.2025.109526","article-title":"Protocol-based fuzzy switching systems with dynamically attack compensation strategy","volume":"520","author":"Xu","year":"2025","journal-title":"Fuzzy Sets Syst."},{"key":"10.1016\/j.fss.2026.109947_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.fss.2025.109661","article-title":"Hierarchical stability and stabilization criteria for delayed T-S fuzzy systems via preassigned-delay-subinterval-based Lyapunov functional","volume":"525","author":"Lin","year":"2026","journal-title":"Fuzzy Sets Syst."},{"key":"10.1016\/j.fss.2026.109947_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.fss.2025.109565","article-title":"Optimal output feedback event-triggered tracking control for Takagi-Sugeno fuzzy systems","volume":"520","author":"Song","year":"2025","journal-title":"Fuzzy Sets Syst."},{"issue":"4","key":"10.1016\/j.fss.2026.109947_bib0005","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1109\/TFUZZ.2025.3585934","article-title":"Multiagent fuzzy reinforcement learning with LLM for cooperative navigation of endovascular robotics","volume":"34","author":"Yao","year":"2026","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"10.1016\/j.fss.2026.109947_bib0006","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1007\/s40815-024-01963-1","article-title":"Reconstructing membership functions for observer-based controller design of Takagi-Sugeno fuzzy model with unmeasured premise variables","volume":"28","author":"Dong","year":"2026","journal-title":"Int. J. Fuzzy Syst."},{"issue":"15","key":"10.1016\/j.fss.2026.109947_bib0007","doi-asserted-by":"crossref","first-page":"6207","DOI":"10.1002\/rnc.8049","article-title":"Robust fault-tolerant tracking control for nonlinear systems using a Takagi-Sugeno fuzzy model based on a state and fault fuzzy observer","volume":"35","author":"Dong","year":"2025","journal-title":"Int. J. Robust Nonlinear Control"},{"key":"10.1016\/j.fss.2026.109947_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.fss.2025.109593","article-title":"Mixed H\u221e\/passive fuzzy control for singularly perturbed semi-Markov jump systems under weighted try-once-discard protocol","volume":"521","author":"Shen","year":"2025","journal-title":"Fuzzy Sets Syst."},{"key":"10.1016\/j.fss.2026.109947_bib0009","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1007\/s40815-024-01803-2","article-title":"Simplified LMI conditions for Takagi-Sugeno fuzzy observer design with unmeasured premise variables","volume":"27","author":"Dong","year":"2025","journal-title":"Int. J. Fuzzy Syst."},{"issue":"2","key":"10.1016\/j.fss.2026.109947_bib0010","first-page":"2231","article-title":"Computational design of interval type-2 fuzzy control for formation and containment of multi-agent systems with collision avoidance capability","volume":"144","author":"Lin","year":"2025","journal-title":"Comput. Model. Eng. Sci."},{"issue":"7","key":"10.1016\/j.fss.2026.109947_bib0011","doi-asserted-by":"crossref","first-page":"4163","DOI":"10.1109\/TFUZZ.2024.3387045","article-title":"Investigating formation and containment problem for nonlinear multiagent systems by interval type-2 fuzzy sliding mode tracking approach","volume":"32","author":"Chang","year":"2024","journal-title":"IEEE Trans. Fuzzy Syst."},{"issue":"8","key":"10.1016\/j.fss.2026.109947_bib0012","doi-asserted-by":"crossref","first-page":"5104","DOI":"10.1109\/TSMC.2023.3325658","article-title":"Data-driven homotopic reinforcement learning-based adaptive optimal control for Markov jump nonlinear systems","volume":"55","author":"Wang","year":"2025","journal-title":"IEEE Trans. Syst., Man, Cybernetics"},{"issue":"10","key":"10.1016\/j.fss.2026.109947_bib0013","doi-asserted-by":"crossref","first-page":"3734","DOI":"10.1109\/TFUZZ.2023.3265666","article-title":"A fuzzy-model-based approach to optimal control for nonlinear Markov jump singularly perturbed systems: a novel integral reinforcement learning scheme","volume":"31","author":"Shen","year":"2023","journal-title":"IEEE Trans. Fuzzy Syst."},{"issue":"4","key":"10.1016\/j.fss.2026.109947_bib0014","doi-asserted-by":"crossref","first-page":"1693","DOI":"10.1109\/TFUZZ.2023.3330484","article-title":"Cooperative design of asynchronous controller and dynamic packet dropouts compensator for strictly dissipative T\u2013S fuzzy Markov jump systems","volume":"32","author":"Wang","year":"2024","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"10.1016\/j.fss.2026.109947_bib0015","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.fss.2022.03.020","article-title":"Fuzzy multi-objective fault-tolerant control for nonlinear Markov jump singularly perturbed systems with persistent dwell-time switched transition probabilities","volume":"452","author":"Shen","year":"2023","journal-title":"Fuzzy Sets Syst."},{"key":"10.1016\/j.fss.2026.109947_bib0016","series-title":"Optimal Control","author":"Lewis","year":"2012"},{"issue":"8","key":"10.1016\/j.fss.2026.109947_bib0017","doi-asserted-by":"crossref","first-page":"2509","DOI":"10.1109\/TFUZZ.2022.3227993","article-title":"Fuzzy control based on reinforcement learning and subsystem error derivatives for strict-feedback systems with an observer","volume":"31","author":"Li","year":"2023","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"10.1016\/j.fss.2026.109947_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.fss.2025.109659","article-title":"Distributed fuzzy adaptive optimal consensus framework for multiagent with imprecise topology via reinforcement learning in graph games","volume":"524","author":"Wang","year":"2026","journal-title":"Fuzzy Sets Syst."},{"key":"10.1016\/j.fss.2026.109947_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.fss.2025.109675","article-title":"Reinforcement learning-based stochastic structurally-sparse sliding mode control for IT-2 T-S fuzzy interconnected multi-area power system","volume":"526","author":"Tang","year":"2026","journal-title":"Fuzzy Sets Syst."},{"issue":"9","key":"10.1016\/j.fss.2026.109947_bib0020","doi-asserted-by":"crossref","first-page":"6049","DOI":"10.1109\/TSMC.2025.3577177","article-title":"Self-learning control for nonlinear Markov jump systems with application to quarter-car suspension model","volume":"55","author":"Qi","year":"2025","journal-title":"IEEE Trans. Syst., Man, Cybernetics"},{"issue":"7","key":"10.1016\/j.fss.2026.109947_bib0021","doi-asserted-by":"crossref","first-page":"4521","DOI":"10.1109\/TCYB.2022.3203795","article-title":"Nonfragile output feedback tracking control for Markov jump fuzzy systems based on integral reinforcement learning scheme","volume":"53","author":"Wang","year":"2023","journal-title":"IEEE Trans. Cybernet."},{"issue":"8","key":"10.1016\/j.fss.2026.109947_bib0022","doi-asserted-by":"crossref","first-page":"8191","DOI":"10.1109\/TCYB.2021.3050619","article-title":"A novel resilient control scheme for a class of Markovian jump systems with partially unknown information","volume":"52","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Cybernet."},{"issue":"12","key":"10.1016\/j.fss.2026.109947_bib0023","doi-asserted-by":"crossref","first-page":"5276","DOI":"10.1109\/TFUZZ.2022.3171844","article-title":"Fuzzy-based adaptive optimization of unknown discrete-time nonlinear Markov jump systems with off-policy reinforcement learning","volume":"30","author":"Fang","year":"2022","journal-title":"IEEE Trans. Fuzzy Syst."},{"issue":"11","key":"10.1016\/j.fss.2026.109947_bib0024","doi-asserted-by":"crossref","first-page":"6388","DOI":"10.1109\/TFUZZ.2024.3449322","article-title":"Optimal control for fuzzy Markov jump singularly perturbed systems: a hybrid zero-sum game iteration approach","volume":"32","author":"Wang","year":"2024","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"10.1016\/j.fss.2026.109947_bib0025","article-title":"Adaptive optimal control of discrete-time systems by reinforcement learning: damping coefficients-based stabilizing policy iterations","volume":"69","author":"Li","year":"2025","journal-title":"Sci. China Inf. Sci."},{"issue":"3","key":"10.1016\/j.fss.2026.109947_bib0026","first-page":"1211","article-title":"Reinforcement learning-based robust tracking control for unknown Markov jump systems and its application","volume":"71","author":"Shen","year":"2024","journal-title":"IEEE Trans. Circuits Syst. II"},{"issue":"4","key":"10.1016\/j.fss.2026.109947_bib0027","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1109\/TAC.1971.1099755","article-title":"An iterative technique for the computation of the steady-state gains for the discrete optimal regulator","volume":"16","author":"Hewer","year":"1971","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.fss.2026.109947_bib0028","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.neucom.2018.05.111","article-title":"Linear quadratic tracking control of unknown discrete-time systems using value iteration algorithm","volume":"314","author":"Li","year":"2018","journal-title":"Neurocomputing"},{"key":"10.1016\/j.fss.2026.109947_bib0029","series-title":"Proc. IEEE 12th Data Driven Control and Learning Systems Conference","first-page":"1141","article-title":"Adaptive optimal control for discrete-time linear systems via hybrid iteration","author":"Qasem","year":"2023"},{"key":"10.1016\/j.fss.2026.109947_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.jfranklin.2025.107959","article-title":"Novel parallel scaling-based policy iteration for H\u221e control of discrete-time markov jump systems","volume":"362","author":"Pang","year":"2025","journal-title":"J. Franklin Inst."},{"key":"10.1016\/j.fss.2026.109947_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2021.110153","article-title":"Homotopic policy iteration-based learning design for unknown linear continuous-time systems","volume":"138","author":"Chen","year":"2022","journal-title":"Automatica"},{"issue":"11","key":"10.1016\/j.fss.2026.109947_bib0032","doi-asserted-by":"crossref","first-page":"13441","DOI":"10.1109\/TII.2024.3435576","article-title":"Off-policy learning H\u221e cooperative optimal output regulation for unknown multiagent systems without initial stabilizing gains","volume":"20","author":"Li","year":"2024","journal-title":"IEEE Trans. Ind. Informatics"},{"issue":"5","key":"10.1016\/j.fss.2026.109947_bib0033","doi-asserted-by":"crossref","first-page":"2922","DOI":"10.1109\/TAC.2023.3235967","article-title":"Efficient off-policy Q-learning for data-based discrete-time LQR problems","volume":"68","author":"Lopez","year":"2023","journal-title":"IEEE Trans. Autom. Control"},{"issue":"3","key":"10.1016\/j.fss.2026.109947_bib0034","doi-asserted-by":"crossref","first-page":"3291","DOI":"10.1109\/TNNLS.2023.3244934","article-title":"Modified \u03bb-policy iteration based adaptive dynamic programming for unknown discrete-time linear systems","volume":"35","author":"Jiang","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"4","key":"10.1016\/j.fss.2026.109947_bib0035","doi-asserted-by":"crossref","first-page":"2746","DOI":"10.1109\/TAC.2025.3631555","article-title":"Cooperative optimal output tracking for discrete-time multiagent systems: stabilizing policy iteration frameworks","volume":"71","author":"Li","year":"2026","journal-title":"IEEE Trans. Autom. Control"},{"issue":"11","key":"10.1016\/j.fss.2026.109947_bib0036","doi-asserted-by":"crossref","first-page":"7380","DOI":"10.1109\/TCYB.2022.3220537","article-title":"Fuzzy H\u221e control of discrete-time nonlinear Markov jump systems via a novel hybrid reinforcement Q-learning method","volume":"53","author":"Wang","year":"2023","journal-title":"IEEE Trans. Cybernet."},{"key":"10.1016\/j.fss.2026.109947_bib0037","article-title":"Zero-sum game-based optimal control for discrete-time Markov jump systems: a parallel off-policy Q-learning method","volume":"467","author":"Wang","year":"2024","journal-title":"Appl. Math. Comput."},{"issue":"7","key":"10.1016\/j.fss.2026.109947_bib0038","doi-asserted-by":"crossref","first-page":"13319","DOI":"10.1109\/TNNLS.2024.3487760","article-title":"Reinforcement learning-based H\u221e control of 2-D Markov jump Roesser systems with optimal disturbance attenuation","volume":"36","author":"Wu","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"22","key":"10.1016\/j.fss.2026.109947_bib0039","doi-asserted-by":"crossref","first-page":"47414","DOI":"10.1109\/JIOT.2025.3602495","article-title":"Learning-based data-driven cooperative adaptive fault-tolerant tracking of heterogeneous multiagent systems","volume":"12","author":"Li","year":"2025","journal-title":"IEEE Inter. Things J."},{"key":"10.1016\/j.fss.2026.109947_bib0040","article-title":"Virtual policy iteration-based H\u221e robust optimal output synchronization for unknown linear multi-agent systems","author":"Li","year":"2026","journal-title":"IEEE CAA J. Automatica Sinica"},{"issue":"11","key":"10.1016\/j.fss.2026.109947_bib0041","doi-asserted-by":"crossref","first-page":"8317","DOI":"10.1109\/TSMC.2025.3605350","article-title":"Adaptive neural network exact-optimal consensus fault tolerant control for nonlinear multiagent systems with actuator faults","volume":"55","author":"Cui","year":"2025","journal-title":"IEEE Trans. Syst., Man, Cybernetics"},{"key":"10.1016\/j.fss.2026.109947_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2019.108672","article-title":"Reinforcement learning and non-zero-sum game output regulation for multi-player linear uncertain systems","volume":"112","author":"Odekunle","year":"2020","journal-title":"Automatica"},{"issue":"4","key":"10.1016\/j.fss.2026.109947_bib0043","doi-asserted-by":"crossref","first-page":"1979","DOI":"10.1109\/TAC.2016.2592802","article-title":"The cooperative output regulation problem of discrete-time linear multi-agent systems by the adaptive distributed observer","volume":"62","author":"Huang","year":"2017","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.fss.2026.109947_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2022.110768","article-title":"Reinforcement learning and cooperative H\u221e output regulation of linear continuous-time multi-agent systems","volume":"148","author":"Jiang","year":"2023","journal-title":"Automatica"},{"issue":"10","key":"10.1016\/j.fss.2026.109947_bib0045","doi-asserted-by":"crossref","first-page":"1986","DOI":"10.1109\/TFUZZ.2019.2893211","article-title":"Adaptive fuzzy fault-tolerant tracking control for partially unknown systems with actuator faults via integral reinforcement learning method","volume":"27","author":"Zhang","year":"2019","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"10.1016\/j.fss.2026.109947_bib0046","doi-asserted-by":"crossref","DOI":"10.1016\/j.fss.2025.109374","article-title":"Packet loss compensation-based fault detection for fuzzy Markov jump systems: a zonotopic residual evaluation approach","volume":"512","author":"Feng","year":"2025","journal-title":"Fuzzy Sets Syst."},{"issue":"2","key":"10.1016\/j.fss.2026.109947_bib0047","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1109\/TFUZZ.2020.3006576","article-title":"Fault detection filtering design for discrete-time interval type-2 T\u2013S fuzzy systems in finite frequency domain","volume":"29","author":"Wang","year":"2021","journal-title":"IEEE Trans. Fuzzy Syst."}],"container-title":["Fuzzy Sets and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0165011426001855?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0165011426001855?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T12:39:00Z","timestamp":1784378340000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0165011426001855"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":47,"alternative-id":["S0165011426001855"],"URL":"https:\/\/doi.org\/10.1016\/j.fss.2026.109947","relation":{},"ISSN":["0165-0114"],"issn-type":[{"value":"0165-0114","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Stabilizing three-phase reinforcement learning for optimal output consensus in stochastic Takagi-Sugeno fuzzy multi-agent systems","name":"articletitle","label":"Article Title"},{"value":"Fuzzy Sets and Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.fss.2026.109947","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":"109947"}}