{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T16:06:38Z","timestamp":1774022798531,"version":"3.50.1"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61803324"],"award-info":[{"award-number":["61803324"]}],"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":["62073275"],"award-info":[{"award-number":["62073275"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1016\/j.ins.2023.118949","type":"journal-article","created":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T11:04:08Z","timestamp":1681729448000},"page":"118949","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":10,"special_numbering":"C","title":["Reinforcement learning based optimal synchronization control for multi-agent systems with input constraints using vanishing viscosity method"],"prefix":"10.1016","volume":"637","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-1137-8634","authenticated-orcid":false,"given":"Dianfeng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaojing","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.ins.2023.118949_br0010","doi-asserted-by":"crossref","first-page":"1170","DOI":"10.1109\/TRO.2007.909810","article-title":"Decentralized cooperative policy for conflict resolution in multivehicle systems","volume":"23","author":"Pallottino","year":"2007","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.ins.2023.118949_br0020","article-title":"Cooperative Control of Multi-Agent Systems: Optimal and Adaptive Design Approaches","author":"Lewis","year":"2013"},{"key":"10.1016\/j.ins.2023.118949_br0030","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1016\/j.ins.2017.07.014","article-title":"Leader-following consensus of discrete-time multiagent systems with time-varying delay based on large delay theory","volume":"417","author":"Liu","year":"2017","journal-title":"Inf. Sci."},{"key":"10.1016\/j.ins.2023.118949_br0040","doi-asserted-by":"crossref","DOI":"10.1201\/b17571","article-title":"Cooperative Control of Multi-Agent Systems: A Consensus Region Approach","author":"Li","year":"2017"},{"key":"10.1016\/j.ins.2023.118949_br0050","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.ins.2021.03.054","article-title":"Secure consensus of multiagent systems with DoS attacks via a graph-based approach","volume":"570","author":"Du","year":"2021","journal-title":"Inf. Sci."},{"key":"10.1016\/j.ins.2023.118949_br0060","doi-asserted-by":"crossref","DOI":"10.1109\/TSG.2023.3237200","article-title":"Multi-agent deep reinforcement learning based distributed optimal generation control of DC microgrids","author":"Fan","year":"2023","journal-title":"IEEE Trans. Smart Grid"},{"key":"10.1016\/j.ins.2023.118949_br0070","article-title":"Multi-objective intelligent energy management for hybrid electric vehicles based on multi-agent reinforcement learning","author":"Yang","year":"2023","journal-title":"IEEE Trans. Transp. Electrif."},{"issue":"3","key":"10.1016\/j.ins.2023.118949_br0080","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1016\/j.automatica.2012.11.003","article-title":"Passivity based synchronization for networked robotic systems with uncertain kinematics and dynamics","volume":"49","author":"Wang","year":"2013","journal-title":"Automatica"},{"issue":"9","key":"10.1016\/j.ins.2023.118949_br0090","doi-asserted-by":"crossref","first-page":"2341","DOI":"10.1016\/j.automatica.2014.07.013","article-title":"Cluster synchronization in directed networks of partial-state coupled linear systems under pinning control","volume":"50","author":"Yu","year":"2014","journal-title":"Automatica"},{"key":"10.1016\/j.ins.2023.118949_br0100","series-title":"Synchronization and Control of Multiagent Systems","author":"Sun","year":"2018"},{"key":"10.1016\/j.ins.2023.118949_br0110","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1016\/j.ins.2021.12.125","article-title":"Optimal consensus model-free control for multi-agent systems subject to input delays and switching topologies","volume":"589","author":"Mehrabian","year":"2022","journal-title":"Inf. Sci."},{"key":"10.1016\/j.ins.2023.118949_br0120","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2022.120563","article-title":"Cooperative energy management and eco-driving of plug-in hybrid electric vehicle via multi-agent reinforcement learning","volume":"332","author":"Wang","year":"2023","journal-title":"Appl. Energy"},{"issue":"3","key":"10.1016\/j.ins.2023.118949_br0130","first-page":"350","article-title":"Test platform and graphical user interface design for vertical take-off and landing drones","volume":"25","author":"Ucgun","year":"2022","journal-title":"Sci. Technol."},{"key":"10.1016\/j.ins.2023.118949_br0140","article-title":"Synchronization: A Universal Concept in Nonlinear Sciences","author":"Pikovsky","year":"2003"},{"issue":"6","key":"10.1016\/j.ins.2023.118949_br0150","doi-asserted-by":"crossref","first-page":"1511","DOI":"10.1109\/TAC.2013.2239011","article-title":"Robust synchronization of uncertain linear multi-agent systems","volume":"58","author":"Trentelman","year":"2013","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.ins.2023.118949_br0160","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.ins.2015.04.044","article-title":"Optimal distributed synchronization control for continuous-time heterogeneous multi-agent differential graphical games","volume":"317","author":"Wei","year":"2015","journal-title":"Inf. Sci."},{"issue":"1","key":"10.1016\/j.ins.2023.118949_br0170","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1109\/TAC.2020.2974424","article-title":"Distributed optimal control for linear multiagent systems on general digraphs","volume":"66","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.ins.2023.118949_br0180","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2022.109081","article-title":"Safe multi-agent deep reinforcement learning for joint bidding and maintenance scheduling of generation units","volume":"232","author":"Rokhforoz","year":"2023","journal-title":"Reliab. Eng. Syst. Saf."},{"issue":"8","key":"10.1016\/j.ins.2023.118949_br0190","doi-asserted-by":"crossref","first-page":"1598","DOI":"10.1016\/j.automatica.2012.05.074","article-title":"Multi-agent differential graphical games: online adaptive learning solution for synchronization with optimality","volume":"48","author":"Vamvoudakis","year":"2012","journal-title":"Automatica"},{"key":"10.1016\/j.ins.2023.118949_br0200","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TSMC.2019.2906902","article-title":"Optimal leader-follower consensus for constrained-input multiagent systems with completely unknown dynamics","author":"Shi","year":"2020","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"10.1016\/j.ins.2023.118949_br0210","series-title":"2020 IEEE 9th Data Driven Control and Learning Systems Conference","article-title":"Distributed optimal coordination control for continuous-time nonlinear multi-agent systems with input constraints","author":"Deng","year":"2020"},{"key":"10.1016\/j.ins.2023.118949_br0220","first-page":"1","article-title":"Distributed adaptive Nash equilibrium solution for differential graphical games","author":"Qian","year":"2021","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.ins.2023.118949_br0230","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1016\/j.ins.2021.08.044","article-title":"Optimal output synchronization of heterogeneous multi-agent systems using measured input-output data","volume":"582","author":"Liu","year":"2022","journal-title":"Inf. Sci."},{"key":"10.1016\/j.ins.2023.118949_br0240","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.automatica.2016.02.002","article-title":"Multi-agent zero-sum differential graphical games for disturbance rejection in distributed control","volume":"69","author":"Jiao","year":"2016","journal-title":"Automatica"},{"key":"10.1016\/j.ins.2023.118949_br0250","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":"5","key":"10.1016\/j.ins.2023.118949_br0260","doi-asserted-by":"crossref","first-page":"4091","DOI":"10.1109\/TIE.2016.2542134","article-title":"Data-driven optimal consensus control for discrete-time multi-agent systems with unknown dynamics using reinforcement learning method","volume":"64","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Ind. Electron."},{"key":"10.1016\/j.ins.2023.118949_br0270","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1016\/j.neucom.2018.06.011","article-title":"Model-free optimal containment control of multi-agent systems based on actor-critic framework","volume":"314","author":"Wang","year":"2018","journal-title":"Neurocomputing"},{"issue":"6","key":"10.1016\/j.ins.2023.118949_br0280","doi-asserted-by":"crossref","first-page":"2139","DOI":"10.1109\/TNNLS.2018.2803059","article-title":"Leader-follower output synchronization of linear heterogeneous systems with active leader using reinforcement learning","volume":"29","author":"Yang","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.ins.2023.118949_br0290","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2022.109636","article-title":"A type-3 fuzzy control for current sharing and voltage balancing in microgrids","volume":"129","author":"Taghieh","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.ins.2023.118949_br0300","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.ins.2021.10.070","article-title":"Reinforcement learning-based control using Q-learning and gravitational search algorithm with experimental validation on a nonlinear servo system","volume":"583","author":"Zamfirache","year":"2022","journal-title":"Inf. Sci."},{"issue":"17","key":"10.1016\/j.ins.2023.118949_br0310","doi-asserted-by":"crossref","first-page":"2838","DOI":"10.1049\/iet-cta.2018.5832","article-title":"Optimal distributed learning for disturbance rejection in networked non-linear games under unknown dynamics","volume":"13","author":"Tatari","year":"2019","journal-title":"IET Control Theory Appl."},{"issue":"5","key":"10.1016\/j.ins.2023.118949_br0320","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1016\/j.automatica.2004.11.034","article-title":"Nearly optimal control laws for nonlinear systems with saturating actuators using a neural network HJB approach","volume":"41","author":"Abu-Khalaf","year":"2005","journal-title":"Automatica"},{"issue":"1","key":"10.1016\/j.ins.2023.118949_br0330","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1109\/TNNLS.2018.2832025","article-title":"Optimal synchronization control of multiagent systems with input saturation via off-policy reinforcement learning","volume":"30","author":"Qin","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.ins.2023.118949_br0340","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/j.automatica.2018.10.038","article-title":"Reinforcement learning for a class of continuous-time input constrained optimal control problems","volume":"99","author":"Yaghmaie","year":"2019","journal-title":"Automatica"},{"issue":"10","key":"10.1016\/j.ins.2023.118949_br0350","doi-asserted-by":"crossref","first-page":"2074","DOI":"10.1109\/TCSI.2004.835655","article-title":"Pinning a complex dynamical network to its equilibrium","volume":"51","author":"Li","year":"2004","journal-title":"IEEE Trans. Circuits Syst. I, Regul. Pap."},{"issue":"9","key":"10.1016\/j.ins.2023.118949_br0360","doi-asserted-by":"crossref","first-page":"1520","DOI":"10.1109\/TAC.2004.834113","article-title":"Consensus problems in networks of agents with switching topology and time-delays","volume":"49","author":"Olfati-Saber","year":"2004","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.ins.2023.118949_br0370","series-title":"Nonlinear H\u221e-Control, Hamiltonian Systems and Hamilton-Jacobi Equations","author":"Aliyu","year":"2011"},{"key":"10.1016\/j.ins.2023.118949_br0380","series-title":"Proceedings of the 7th ACM Conference on Electronic Commerce","article-title":"Nash equilibria in graphical games on trees revisited","author":"Elkind","year":"2006"},{"key":"10.1016\/j.ins.2023.118949_br0390","series-title":"Optimal Control, EngineeringPro Collection","author":"Lewis","year":"2012"},{"key":"10.1016\/j.ins.2023.118949_br0400","series-title":"Cooperative Control of Multi-Agent Systems: Optimal and Adaptive Design Approaches","author":"Lewis","year":"2014"},{"key":"10.1016\/j.ins.2023.118949_br0410","series-title":"Dynamic Programming and Optimal Control, Athena Scientific","author":"Bertsekas","year":"1995"},{"issue":"1","key":"10.1016\/j.ins.2023.118949_br0420","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1090\/S0002-9947-1983-0690039-8","article-title":"Viscosity solutions of Hamilton-Jacobi equations","volume":"277","author":"Crandall","year":"1983","journal-title":"Trans. Am. Math. Soc."},{"issue":"5","key":"10.1016\/j.ins.2023.118949_br0430","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1016\/j.isatra.2013.04.004","article-title":"A policy iteration approach to online optimal control of continuous-time constrained-input systems","volume":"52","author":"Modares","year":"2013","journal-title":"ISA Trans."},{"issue":"3\u20135","key":"10.1016\/j.ins.2023.118949_br0440","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1002\/acs.2348","article-title":"Online solution of nonquadratic two-player zero-sum games arising in the H\u221e control of constrained input systems","volume":"28","author":"Modares","year":"2014","journal-title":"Int. J. Adapt. Control Signal Process."},{"key":"10.1016\/j.ins.2023.118949_br0450","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1016\/j.neunet.2015.08.007","article-title":"Reinforcement learning solution for HJB equation arising in constrained optimal control problem","volume":"71","author":"Luo","year":"2015","journal-title":"Neural Netw."},{"issue":"5","key":"10.1016\/j.ins.2023.118949_br0460","doi-asserted-by":"crossref","first-page":"878","DOI":"10.1016\/j.automatica.2010.02.018","article-title":"Online actor\u2013critic algorithm to solve the continuous-time infinite horizon optimal control problem","volume":"46","author":"Vamvoudakis","year":"2010","journal-title":"Automatica"},{"key":"10.1016\/j.ins.2023.118949_br0470","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.neucom.2017.03.047","article-title":"Neural-network-based adaptive guaranteed cost control of nonlinear dynamical systems with matched uncertainties","volume":"245","author":"Mu","year":"2017","journal-title":"Neurocomputing"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0020025523005182?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0020025523005182?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T06:07:17Z","timestamp":1758089237000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025523005182"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":47,"alternative-id":["S0020025523005182"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.ins.2023.118949","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2023,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Reinforcement learning based optimal synchronization control for multi-agent systems with input constraints using vanishing viscosity method","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.ins.2023.118949","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"118949"}}