{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:56:55Z","timestamp":1778345815070,"version":"3.51.4"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"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":["61903209"],"award-info":[{"award-number":["61903209"]}],"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":["61873138"],"award-info":[{"award-number":["61873138"]}],"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":["61573205"],"award-info":[{"award-number":["61573205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Qingdao Postdoctoral Applied Research Project with Name"},{"DOI":"10.13039\/501100007129","name":"Shandong Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["ZR2019MF063"],"award-info":[{"award-number":["ZR2019MF063"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Support Plan for Youth Innovation of Universities in Shandong Province","award":["2019KJN033"],"award-info":[{"award-number":["2019KJN033"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1109\/tnnls.2020.3025711","type":"journal-article","created":{"date-parts":[[2020,10,7]],"date-time":"2020-10-07T19:24:18Z","timestamp":1602098658000},"page":"4639-4652","source":"Crossref","is-referenced-by-count":85,"title":["Learning Automata-Based Multiagent Reinforcement Learning for Optimization of Cooperative Tasks"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6615-629X","authenticated-orcid":false,"given":"Zhen","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8856-4289","authenticated-orcid":false,"given":"Dongqing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8870-2960","authenticated-orcid":false,"given":"Junwei","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9781118884614.ch4"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-72428-7_1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14834-7_7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-012-0420-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-013-9206-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1142\/S0218213015500232"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2016.06.028"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-016-0788-0"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2016.12.006"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2017.09.008"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.elerap.2016.10.002"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/dac.2648"},{"key":"ref14","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","volume-title":"Proc. AAAI","author":"Claus"},{"key":"ref15","first-page":"326","article-title":"Reinforcement learning of coordination in cooperative multi-agent systems","volume-title":"Proc. AAAI","author":"Kapetanakis"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/7172614"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2932203"},{"key":"ref18","first-page":"541","article-title":"Nash convergence of gradient dynamics in general-sum games","volume-title":"Proc. UAI","author":"Singh"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"ref20","first-page":"928","article-title":"Online convex programming and generalized infinitesimal gradient ascent","volume-title":"Proc. ICML","author":"Zinkevich"},{"key":"ref21","first-page":"209","article-title":"Convergence and no-regret in multiagent learning","volume-title":"Proc. NIPS","volume":"17","author":"Bowling"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1017\/S026988890500041X"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.01.004"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4818"},{"issue":"4","key":"ref25","first-page":"1145","article-title":"Dynamics of Boltzmann Q-learning in two-agent two-action games","volume":"85","author":"Kianercy","year":"2012","journal-title":"Phys. Rev. E, Stat. Phys. Plasmas Fluids Relat. Interdiscip. Top."},{"key":"ref26","article-title":"Q-learning in two-player two-action games","volume-title":"Proc. AAMAS","author":"Babes"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/21.293490"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.920998"},{"key":"ref29","first-page":"1151","article-title":"Multi-agent reinforcement learning for traffic light control","volume-title":"Proc. ICML","author":"Wiering"},{"key":"ref30","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":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2609500"},{"issue":"2","key":"ref32","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1023\/A:1007518724497","article-title":"Elevator group control using multiple reinforcement learning agents","volume":"33","author":"Crites","year":"1998","journal-title":"Mach. Learn."},{"key":"ref33","first-page":"1571","article-title":"Reinforcement learning to play an optimal Nash equilibrium in team Markov games","volume-title":"Proc. NIPS","volume":"15","author":"Wang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2544866"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2878853"},{"key":"ref36","article-title":"Counterfactual multi-agent policy gradients","volume-title":"arXiv:1705.08926","author":"Foerster","year":"2017"},{"key":"ref37","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/DDCLS.2018.8516035"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.047"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2016.7524910"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029969"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2332042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7639"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2628"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-015-9447-5"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-017-0716-8"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2688452"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8815076"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-010-0189-2_4"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-011-3760-7_1"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69291-1_7"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1057\/9780230280847_30"},{"key":"ref53","first-page":"4878","article-title":"Multi-agent Q-learning with joint state value approximation","volume-title":"Proc. CCC","author":"Chen"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1082473.1082631"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2002.1176414"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9559436\/09216601.pdf?arnumber=9216601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T00:50:22Z","timestamp":1706057422000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9216601\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":55,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.3025711","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10]]}}}