{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T04:40:21Z","timestamp":1760330421364,"version":"build-2065373602"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Youth Talent Project of Scientific Research Program of Hubei Provincial Department of Education","award":["Q20241809"],"award-info":[{"award-number":["Q20241809"]}]},{"name":"Doctoral Scientific Research Foundation of Hubei University of Automotive Technology","award":["202404"],"award-info":[{"award-number":["202404"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-07885-5","type":"journal-article","created":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T15:47:26Z","timestamp":1760284046000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Homotopic reinforcement learning for distributed consensus control of stochastic Markov jump multi-agent systems"],"prefix":"10.1007","volume":"81","author":[{"given":"Zheng","family":"Yao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiwu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengjie","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"7885_CR1","unstructured":"Hua M, Yao X-Y, Liu W-J, Geng M-J, Lv M. Optimizing fixed-time generalized nash equilibrium seeking in multi-unmanned aerial vehicle games. IEEE Trans. Aerosp. Electron. Syst., 10\u2013110920253526559"},{"issue":"4","key":"7885_CR2","first-page":"3447","volume":"11","author":"P Wang","year":"2020","unstructured":"Wang P, Govindarasu M (2020) Multi-agent based attack-resilient system integrity protection for smart grid. IEEE Trans Automation Sci Eng 11(4):3447\u20133456","journal-title":"IEEE Trans Automation Sci Eng"},{"issue":"2","key":"7885_CR3","doi-asserted-by":"publisher","first-page":"1299","DOI":"10.1109\/TIE.2015.2453412","volume":"63","author":"Y Tang","year":"2015","unstructured":"Tang Y, Xing X, Karimi HR, Kocarev L, Kurths J (2015) Tracking control of networked multi-agent systems under new characterizations of impulses and its applications in robotic systems. IEEE Trans Ind Electron 63(2):1299\u20131307","journal-title":"IEEE Trans Ind Electron"},{"issue":"5","key":"7885_CR4","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1007\/s11227-025-07171-4","volume":"81","author":"G Xie","year":"2025","unstructured":"Xie G, Chen L, Li Y (2025) Multi-agent consensus algorithm based on pruned topology. J Supercomput 81(5):684","journal-title":"J Supercomput"},{"issue":"14","key":"7885_CR5","doi-asserted-by":"publisher","first-page":"15882","DOI":"10.1007\/s11227-022-04514-3","volume":"78","author":"T Geng","year":"2022","unstructured":"Geng T, Du Y (2022) Applying the blockchain-based deep reinforcement consensus algorithm to the intelligent manufacturing model under internet of things. J Supercomput 78(14):15882\u201315904","journal-title":"J Supercomput"},{"issue":"3","key":"7885_CR6","doi-asserted-by":"publisher","first-page":"883","DOI":"10.1016\/j.automatica.2013.12.008","volume":"50","author":"Z Li","year":"2014","unstructured":"Li Z, Duan Z, Lewis FL (2014) Distributed robust consensus control of multi-agent systems with heterogeneous matching uncertainties. Automatica 50(3):883\u2013889","journal-title":"Automatica"},{"key":"7885_CR7","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.ins.2018.02.008","volume":"439","author":"A-Y Lu","year":"2018","unstructured":"Lu A-Y, Yang G-H (2018) Distributed consensus control for multi-agent systems under denial-of-service. Inf Sci 439:95\u2013107","journal-title":"Inf Sci"},{"issue":"9","key":"7885_CR8","doi-asserted-by":"publisher","first-page":"2898","DOI":"10.1016\/j.automatica.2013.06.017","volume":"49","author":"J Qin","year":"2013","unstructured":"Qin J, Yu C (2013) Cluster consensus control of generic linear multi-agent systems under directed topology with acyclic partition. Automatica 49(9):2898\u20132905","journal-title":"Automatica"},{"issue":"8","key":"7885_CR9","doi-asserted-by":"publisher","first-page":"3339","DOI":"10.1109\/TNNLS.2017.2728622","volume":"29","author":"J Zhang","year":"2017","unstructured":"Zhang J, Zhang H, Feng T (2017) Distributed optimal consensus control for nonlinear multiagent system with unknown dynamic. IEEE Trans Neural Netw Learn Syst 29(8):3339\u20133348","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"10","key":"7885_CR10","doi-asserted-by":"publisher","first-page":"12202","DOI":"10.1007\/s11227-022-04356-z","volume":"78","author":"J-W Park","year":"2022","unstructured":"Park J-W, Kwon M-W, Hong T (2022) Queue congestion prediction for large-scale high performance computing systems using a hidden Markov model. J Supercomput 78(10):12202\u201312223","journal-title":"J Supercomput"},{"key":"7885_CR11","doi-asserted-by":"publisher","first-page":"1354","DOI":"10.1007\/s11227-020-03329-4","volume":"77","author":"Z Wang","year":"2021","unstructured":"Wang Z, Guo N, Wang S, Xu Y (2021) Prediction of highway asphalt pavement performance based on Markov chain and artificial neural network approach. J Supercomput 77:1354\u20131376","journal-title":"J Supercomput"},{"issue":"4","key":"7885_CR12","doi-asserted-by":"publisher","first-page":"1497","DOI":"10.1007\/s11227-018-2235-7","volume":"74","author":"J Bylina","year":"2018","unstructured":"Bylina J (2018) Parallelization of stochastic bounds for Markov chains on multicore and manycore platforms. J Supercomput 74(4):1497\u20131509","journal-title":"J Supercomput"},{"issue":"9","key":"7885_CR13","doi-asserted-by":"publisher","first-page":"1959","DOI":"10.1080\/00207721.2024.2328073","volume":"55","author":"L Kang","year":"2024","unstructured":"Kang L, Ji Z, Liu Y, Lin C (2024) Consensus of stochastic multi-agent systems with time-delay and Markov jump. Int J Syst Sci 55(9):1959\u20131979","journal-title":"Int J Syst Sci"},{"key":"7885_CR14","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.neucom.2018.01.075","volume":"287","author":"R Sakthivel","year":"2018","unstructured":"Sakthivel R, Sakthivel R, Kaviarasan B, Alzahrani F (2018) Leader-following exponential consensus of input saturated stochastic multi-agent systems with Markov jump parameters. Neurocomputing 287:84\u201392","journal-title":"Neurocomputing"},{"key":"7885_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109177","volume":"121","author":"VG Lopez","year":"2020","unstructured":"Lopez VG, Lewis FL, Wan Y, Liu M, Hewer G, Estabridis K (2020) Stability and robustness analysis of minmax solutions for differential graphical games. Automatica 121:109177","journal-title":"Automatica"},{"issue":"8","key":"7885_CR16","doi-asserted-by":"publisher","first-page":"10455","DOI":"10.1007\/s11227-022-04305-w","volume":"78","author":"M Mahdavimoghadam","year":"2022","unstructured":"Mahdavimoghadam M, Nikanjam A, Abdoos M (2022) Improved reinforcement learning in cooperative multi-agent environments using knowledge transfer. J Supercomput 78(8):10455\u201310479","journal-title":"J Supercomput"},{"issue":"3","key":"7885_CR17","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1109\/TPWRS.2004.831259","volume":"19","author":"JG Vlachogiannis","year":"2004","unstructured":"Vlachogiannis JG, Hatziargyriou ND (2004) Reinforcement learning for reactive power control. IEEE Trans Power Syst 19(3):1317\u20131325","journal-title":"IEEE Trans Power Syst"},{"issue":"8","key":"7885_CR18","doi-asserted-by":"publisher","first-page":"10720","DOI":"10.1007\/s11227-023-05854-4","volume":"80","author":"F Fathinezhad","year":"2024","unstructured":"Fathinezhad F, Adibi P, Shoushtarian B, Chanussot J (2024) Local and soft feature selection for value function approximation in batch reinforcement learning for robot navigation. J Supercomput 80(8):10720\u201310745","journal-title":"J Supercomput"},{"key":"7885_CR19","first-page":"228","volume":"72","author":"S Hu","year":"2025","unstructured":"Hu S, Luo Y, Xie X, Zhang H (2025) $$H_{\\infty }$$ optimal load frequency control of power system: a novel model-free approach. IEEE Trans Circuits Syst II Exp Briefs 72:228\u2013232","journal-title":"IEEE Trans Circuits Syst. II Exp Briefs"},{"key":"7885_CR20","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling LP, Littman ML, Moore AW (1996) Reinforcement learning: a survey. J Artif Intell Res 4:237\u2013285","journal-title":"J Artif Intell Res"},{"issue":"1","key":"7885_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11227-007-0135-3","volume":"43","author":"D Vengerov","year":"2008","unstructured":"Vengerov D (2008) A reinforcement learning framework for online data migration in hierarchical storage systems. J Supercomput 43(1):1\u201319","journal-title":"J Supercomput"},{"issue":"6","key":"7885_CR22","doi-asserted-by":"publisher","first-page":"2042","DOI":"10.1109\/TNNLS.2017.2773458","volume":"29","author":"B Kiumarsi","year":"2017","unstructured":"Kiumarsi B, Vamvoudakis KG, Modares H, Lewis FL (2017) Optimal and autonomous control using reinforcement learning: a survey. IEEE Trans Neural Netw Learn Syst 29(6):2042\u20132062","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"7885_CR23","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1109\/TSMCB.2006.883869","volume":"37","author":"P He","year":"2007","unstructured":"He P, Jagannathan S (2007) Reinforcement learning neural-network-based controller for nonlinear discrete-time systems with input constraints. IEEE Trans Syst Man Cybern Syst 37:425\u2013436","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"issue":"2","key":"7885_CR24","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, Lewis FL (2009) Adaptive optimal control for continuous-time linear systems based on policy iteration. Automatica 45(2):477\u2013484","journal-title":"Automatica"},{"issue":"10","key":"7885_CR25","doi-asserted-by":"publisher","first-page":"2699","DOI":"10.1016\/j.automatica.2012.06.096","volume":"48","author":"Y Jiang","year":"2012","unstructured":"Jiang Y, Jiang Z-P (2012) Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics. Automatica 48(10):2699\u20132704","journal-title":"Automatica"},{"key":"7885_CR26","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1016\/j.automatica.2016.05.003","volume":"71","author":"T Bian","year":"2016","unstructured":"Bian T, Jiang Z-P (2016) Value iteration and adaptive dynamic programming for data-driven adaptive optimal control design. Automatica 71:348\u2013360","journal-title":"Automatica"},{"key":"7885_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.110153","volume":"138","author":"C Chen","year":"2022","unstructured":"Chen C, Lewis FL, Li B (2022) Homotopic policy iteration-based learning design for unknown linear continuous-time systems. Automatica 138:110153","journal-title":"Automatica"},{"issue":"5","key":"7885_CR28","doi-asserted-by":"publisher","first-page":"3396","DOI":"10.1109\/TAC.2023.3339660","volume":"69","author":"C Chen","year":"2024","unstructured":"Chen C, Lewis FL, Xie K, Xie S (2024) Adaptive optimal control of unknown nonlinear systems via homotopy-based policy iteration. IEEE Trans Autom Control 69(5):3396\u20133403","journal-title":"IEEE Trans Autom Control"},{"key":"7885_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120615","volume":"670","author":"H Wang","year":"2024","unstructured":"Wang H, Qin G, Cheng J, Tang S (2024) Homotopic adp based $$H_{\\infty }$$ integral sliding mode secure control for Markov jumping cyber-physical systems. Inf Sci 670:120615","journal-title":"Inf Sci"},{"issue":"11","key":"7885_CR30","doi-asserted-by":"publisher","first-page":"13441","DOI":"10.1109\/TII.2024.3435576","volume":"20","author":"D Li","year":"2024","unstructured":"Li D, Dong J (2024) Off-policy learning $$H_{\\infty }$$ cooperative optimal output regulation for unknown multiagent systems without initial stabilizing gains. IEEE Trans Ind Informat 20(11):13441\u201313451","journal-title":"IEEE Trans Ind Informat"},{"key":"7885_CR31","first-page":"1","volume":"8","author":"J Liu","year":"2024","unstructured":"Liu J, Mi X, Xia J, Su L, Shen H (2024) A homotopy-based reinforcement learning scheme to optimal control for Markov switched interconnected systems. J Control Decis 8:1\u201316","journal-title":"J Control Decis"},{"key":"7885_CR32","doi-asserted-by":"crossref","unstructured":"Ren W, Beard RW (2008) Distributed Consensus in Multi-vehicle Cooperative Control: Theory and Applications. Springer,","DOI":"10.1007\/978-1-84800-015-5"},{"issue":"03","key":"7885_CR33","doi-asserted-by":"publisher","first-page":"2150011","DOI":"10.1142\/S2737480721500114","volume":"1","author":"W Dong","year":"2021","unstructured":"Dong W, Wang J, Wang C, Qi Z, Ding Z (2021) Graphical minimax game and off-policy reinforcement learning for heterogeneous mass with spanning tree condition. Guid Navig Control 1(03):2150011","journal-title":"Guid Navig Control"},{"issue":"3","key":"7885_CR34","doi-asserted-by":"publisher","first-page":"3265","DOI":"10.1109\/TNNLS.2022.3215629","volume":"35","author":"B Lian","year":"2024","unstructured":"Lian B, Donge VS, Xue W, Lewis FL, Davoudi A (2024) Distributed minmax strategy for multiplayer games: stability, robustness, and algorithms. IEEE Trans Neural Netw Learn Syst 35(3):3265\u20133277","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"12","key":"7885_CR35","doi-asserted-by":"publisher","first-page":"7804","DOI":"10.1109\/TCYB.2024.3403680","volume":"54","author":"Z Ming","year":"2024","unstructured":"Ming Z, Zhang H, Wang Y, Dai J (2024) Policy iteration q-learning for linear It\u00f4 stochastic systems with Markovian jumps and its application to power systems. IEEE Trans Cybern 54(12):7804\u20137813","journal-title":"IEEE Trans Cybern"},{"issue":"8","key":"7885_CR36","doi-asserted-by":"publisher","first-page":"1577","DOI":"10.1007\/s11431-020-1668-4","volume":"63","author":"C Ma","year":"2020","unstructured":"Ma C, Li Z, Wu W, Zhang Y (2020) Iterative algorithms with the latest update for riccati matrix equations in It\u00f4 Markov jump systems. Sci China Technol Sci 63(8):1577\u20131584","journal-title":"Sci China Technol Sci"},{"issue":"12","key":"7885_CR37","doi-asserted-by":"publisher","first-page":"1431","DOI":"10.1049\/iet-cta.2015.0973","volume":"10","author":"J Song","year":"2016","unstructured":"Song J, He S, Liu F, Niu Y, Ding Z (2016) Data-driven policy iteration algorithm for optimal control of continuous-time It\u00f4 stochastic systems with Markovian jumps. IET Control Theory Appl 10(12):1431\u20131439","journal-title":"IET Control Theory Appl"},{"issue":"12","key":"7885_CR38","doi-asserted-by":"publisher","first-page":"7635","DOI":"10.1109\/TCYB.2022.3186886","volume":"53","author":"H Fang","year":"2023","unstructured":"Fang H, Zhang M, He S, Luan X, Liu F, Ding Z (2023) Solving the zero-sum control problem for tidal turbine system: an online reinforcement learning approach. IEEE Trans Cybern 53(12):7635\u20137647","journal-title":"IEEE Trans Cybern"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07885-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-07885-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07885-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T04:02:27Z","timestamp":1760328147000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-07885-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":38,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["7885"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-07885-5","relation":{},"ISSN":["1573-0484"],"issn-type":[{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"27 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The authors claim that there are no ethical issues involved in this research.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"1446"}}