{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T20:58:01Z","timestamp":1783025881304,"version":"3.54.6"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673107"],"award-info":[{"award-number":["61673107"]}],"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":["62073076"],"award-info":[{"award-number":["62073076"]}],"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":["62073074"],"award-info":[{"award-number":["62073074"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Provincial Key Laboratory of Networked Collective Intelligence","award":["BM2017002"],"award-info":[{"award-number":["BM2017002"]}]},{"name":"Double Innovation Plan","award":["4207012004"],"award-info":[{"award-number":["4207012004"]}]},{"name":"Special Funding for Overseas Talents","award":["6207011901"],"award-info":[{"award-number":["6207011901"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tnnls.2021.3139138","type":"journal-article","created":{"date-parts":[[2022,1,11]],"date-time":"2022-01-11T20:35:12Z","timestamp":1641933312000},"page":"7210-7221","source":"Crossref","is-referenced-by-count":30,"title":["Distributed Actor\u2013Critic Algorithms for Multiagent Reinforcement Learning Over Directed Graphs"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1455-7216","authenticated-orcid":false,"given":"Pengcheng","family":"Dai","sequence":"first","affiliation":[{"name":"School of Mathematics, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6406-2399","authenticated-orcid":false,"given":"Wenwu","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Mathematics and the School of Automation, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3065-393X","authenticated-orcid":false,"given":"He","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mathematics, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9752-8925","authenticated-orcid":false,"given":"Simone","family":"Baldi","sequence":"additional","affiliation":[{"name":"School of Mathematics, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Distributed Q-learning algorithm for dynamic resource allocation with unknown objective functions and application to microgrid","author":"dai","year":"2021","journal-title":"IEEE Trans Cybern"},{"key":"ref35","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","author":"wang","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2933443"},{"key":"ref34","first-page":"7613","article-title":"MAVEN: Multi-agent variational exploration","author":"mahajan","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.12.020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619581"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.04.082"},{"key":"ref36","first-page":"5867","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"2018","journal-title":"Proc 17th Int Conf Auton Agents MultiAgent Syst"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2241057"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2921475"},{"key":"ref33","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"son","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2837338"},{"key":"ref32","first-page":"6846","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref2","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9781118453988.ch4"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-33384-3","article-title":"Multi-agent reinforcement learning: A selective overview of theories and algorithms","author":"zhang","year":"2020","journal-title":"Studies Syst Decision Control Handbook RL Control"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2020.3018871"},{"key":"ref38","first-page":"2603","article-title":"An emphatic approach to the problem of off-policy temporal-difference learning","volume":"17","author":"sutton","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref19","first-page":"535","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","volume":"2","author":"lauer","year":"0","journal-title":"Proc 17th Int Conf Mach Learn (ICML)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2019.2933578"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2995154"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.3004009"},{"key":"ref25","article-title":"Distributed stabilization of heterogeneous MASs in uncertain strong-weak competition networks","author":"hu","year":"2020","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"ref20","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"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2364096"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.07.020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2926115"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2004.834113"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-93-86279-38-5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.01.001"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2010.2041686"},{"key":"ref8","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2247627"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2585520"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.05.031"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2401334"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2320744"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029257"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10273172\/09677456.pdf?arnumber=9677456","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:15:13Z","timestamp":1698084913000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9677456\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":43,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3139138","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}