{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:24:11Z","timestamp":1785335051426,"version":"3.55.0"},"reference-count":54,"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":"am","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":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876023"],"award-info":[{"award-number":["61876023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ECCS 1917275"],"award-info":[{"award-number":["ECCS 1917275"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1109\/tcyb.2020.3025491","type":"journal-article","created":{"date-parts":[[2020,10,23]],"date-time":"2020-10-23T19:36:52Z","timestamp":1603481812000},"page":"4994-5007","source":"Crossref","is-referenced-by-count":33,"title":["Multiagent Adversarial Collaborative Learning via Mean-Field Theory"],"prefix":"10.1109","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1912-8536","authenticated-orcid":false,"given":"Guiyang","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5247-9370","authenticated-orcid":false,"given":"Haibo","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-9533","authenticated-orcid":false,"given":"Jinglin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9185-3989","authenticated-orcid":false,"given":"Fei-Yue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"4686","article-title":"Decentralised learning in systems with many, many strategic agents","author":"mguni","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref38","first-page":"1495","article-title":"Emergence of grounded compositional language in multi-agent populations","author":"mordatch","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref32","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume":"32","author":"silver","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref31","author":"papoudakis","year":"2019","journal-title":"Dealing with nonstationarity in multi-agent deep reinforcement learning"},{"key":"ref30","first-page":"322","article-title":"Friend-or-foe Q-learning in general-sum games","volume":"1","author":"littman","year":"2001","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","author":"singh","year":"2018","journal-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks"},{"key":"ref36","first-page":"122","article-title":"Learning with opponent-learning awareness","author":"foerster","year":"2018","journal-title":"Proc 17th Int Conf Auton Agents MultiAgent Syst"},{"key":"ref35","first-page":"4257","article-title":"Modeling others using oneself in multi-agent reinforcement learning","volume":"80","author":"raileanu","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref34","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","author":"he","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref29","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume":"70","author":"pinto","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref1","volume":"17","author":"lewis","year":"2013","journal-title":"Reinforcement Learning and Approximate Dynamic Programming for Feedback Control"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.01.002"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2544866"},{"key":"ref21","author":"foerster","year":"2016","journal-title":"Learning to communicate to solve riddles with deep distributed recurrent q-networks"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref23","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref26","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","volume":"70","author":"omidshafiei","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref25","first-page":"535","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"2000","journal-title":"Proc 17th Int Conf Mach Learn"},{"key":"ref50","first-page":"8222","article-title":"MAgent: A many-agent reinforcement learning platform for artificial collective intelligence","author":"zheng","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref51","first-page":"29","article-title":"Deep recurrent Q-learning for partially observable MDPs","author":"hausknecht","year":"2015","journal-title":"Proc AAAI Fall Symp Series"},{"key":"ref54","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":"ref53","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1185"},{"key":"ref52","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2014.2310238"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2868715"},{"key":"ref40","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume":"80","author":"yang","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03098-8_30"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9383-6"},{"key":"ref14","first-page":"16","article-title":"A comparison of various approaches to reinforcement learning algorithms for multi-robot box pushing","author":"rahimi","year":"2018","journal-title":"Proc Int Conf Eng Res Appl"},{"key":"ref15","article-title":"Coordinated deep reinforcement learners for traffic light control","author":"van der pol","year":"2016","journal-title":"Proc Learn Inference Control Multi-Agent Syst (NIPS)"},{"key":"ref16","author":"shalev-shwartz","year":"2016","journal-title":"Safe Multi-Agent Reinforcement Learning for Autonomous Driving"},{"key":"ref17","author":"corder","year":"2019","journal-title":"Decentralized multi-agent actor-critic with generative inference"},{"key":"ref18","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","first-page":"2974","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.08.120"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2303139"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/asjc.1102"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.920269"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2781130"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref49","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2932203"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s10955-009-9814-1"},{"key":"ref45","first-page":"89","article-title":"Convergence problems of general-sum multiagent reinforcement learning","author":"bowling","year":"2000","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3084454"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2964791.2901463"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref41","first-page":"12102","article-title":"Modelling the dynamics of multiagent q-learning in repeated symmetric games: a mean field theoretic approach","author":"hu","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"ref43","first-page":"242","article-title":"Multiagent reinforcement learning: Theoretical framework and an algorithm","volume":"98","author":"hu","year":"1998","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6221036\/9568742\/9238422-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/9568742\/09238422.pdf?arnumber=9238422","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:23Z","timestamp":1652194403000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9238422\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":54,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2020.3025491","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10]]}}}