{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T07:56:19Z","timestamp":1781164579900,"version":"3.54.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["62366058"],"award-info":[{"award-number":["62366058"]}],"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":["6250076060"],"award-info":[{"award-number":["6250076060"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Yunnan Province XingDian Talent Support Program","award":["YNWR-QNBJ-2020-041"],"award-info":[{"award-number":["YNWR-QNBJ-2020-041"]}]},{"name":"Young and Middle-Aged Academic and Technical Leaders Reserve Talent Project of Yunnan Province","award":["202205AC160034"],"award-info":[{"award-number":["202205AC160034"]}]},{"DOI":"10.13039\/501100004329","name":"Slovenian Research and Innovation Agency","doi-asserted-by":"crossref","award":["P1-0403"],"award-info":[{"award-number":["P1-0403"]}],"id":[{"id":"10.13039\/501100004329","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tnnls.2025.3641365","type":"journal-article","created":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T18:37:52Z","timestamp":1767292672000},"page":"2854-2868","source":"Crossref","is-referenced-by-count":4,"title":["Dynamics of\n                    <i>Q<\/i>\n                    -Learning in Networked Stochastic Games"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9977-9401","authenticated-orcid":false,"given":"Zheng","family":"Yuan","sequence":"first","affiliation":[{"name":"School of Cybersecurity, Northwestern Polytechnical University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7612-5975","authenticated-orcid":false,"given":"Guangchen","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Cybersecurity, Northwestern Polytechnical University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1908-1344","authenticated-orcid":false,"given":"Shuyue","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Basic Theoretical Research, Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3087-541X","authenticated-orcid":false,"given":"Matja\u017e","family":"Perc","sequence":"additional","affiliation":[{"name":"Faculty of Natural Sciences and Mathematics, University of Maribor, Maribor, Slovenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Chu","sequence":"additional","affiliation":[{"name":"School of Statistics and Mathematics, Yunnan University of Finance and Economics, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3891-4663","authenticated-orcid":false,"given":"Jinzhuo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software and AI, Yunnan University, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3051163"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.65109\/qmsu8421"},{"key":"ref5","first-page":"3646","article-title":"A multi-agent reinforcement learning model of common-pool resource appropriation","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Perolat"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abk2607"},{"key":"ref7","article-title":"Understanding the world to solve social dilemmas using multi-agent reinforcement learning","author":"Rios","year":"2023","journal-title":"arXiv:2305.11358"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1126\/science.aay2400"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4818"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1006\/jeth.1997.2319"},{"key":"ref13","first-page":"3532","article-title":"Multiplicative weights updates with constant step-size in graphical constant-sum games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Cheung"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-35389-6_7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.65109\/ENZT1484"},{"key":"ref16","first-page":"26318","article-title":"Exploration-exploitation in multi-agent competition: Convergence with bounded rationality","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Leonardos"},{"key":"ref17","first-page":"10450","article-title":"Poincar\u00e9 recurrence, cycles and spurious equilibria in gradient-descent-ascent for non-convex non-concave zero-sum games","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Flokas"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2941229"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-031219-041220"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.15167"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/860575.860687"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.01.004"},{"key":"ref24","first-page":"12102","article-title":"Modelling the dynamics of multiagent Q-learning in repeated symmetric games: A mean field theoretic approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Hu"},{"key":"ref25","article-title":"The evolutionary dynamics of independent learning agents in population games","author":"Hu","year":"2020","journal-title":"arXiv:2006.16068"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.65109\/mlbh9101"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1126\/science.162.3859.1243"},{"key":"ref28","article-title":"On the near-optimality of local policies in large cooperative multi-agent reinforcement learning","author":"Uddin Mondal","year":"2022","journal-title":"arXiv:2209.03491"},{"key":"ref29","first-page":"5567","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Yang"},{"key":"ref30","article-title":"Evolutionary population curriculum for scaling multi-agent reinforcement learning","author":"Long","year":"2020","journal-title":"arXiv:2003.10423"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3236361"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0277-x"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2020.0639"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.65109\/rbsy8382"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i5.25691"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/359826a0"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1126\/science.1133755"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/28"},{"key":"ref40","first-page":"1","article-title":"On the approximation of cooperative heterogeneous multi-agent reinforcement learning (MARL) using mean field control (MFC)","author":"Mondal","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-39625-9"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2307\/1882186"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.67.015206"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553422"},{"key":"ref45","first-page":"1167","article-title":"Classes of multiagent Q-learning dynamics with epsilon-greedy exploration","volume-title":"Proc. 27th Int. Conf. Mach. Learn. (ICML)","author":"Wunder"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.9012"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.65109\/cuia8160"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.65109\/vlue9705"},{"key":"ref49","first-page":"8","article-title":"RESQ-learning in stochastic games","volume-title":"Proc. Adapt. Learn. Agents Workshop AAMAS","author":"Hennes"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/55"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4289-6"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2024.3473941"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/76"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3374"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3565266"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/0047-2484(92)90081-J"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X00032325"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1707505115"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1038\/nature04605"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtbi.2008.01.005"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1908936116"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2023.3279094"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-49505-5"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3439372"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1038\/nature06940"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.biosystems.2009.10.003"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.physrep.2020.05.004"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.physrep.2021.10.005"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.81.036115"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-025-02289-0"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-04968-1"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.physrep.2007.04.004"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.80.046106"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.85.026104"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1093\/pnasnexus\/pgae326"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128514"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11549955\/11321308.pdf?arnumber=11321308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:56:40Z","timestamp":1780603000000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11321308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":76,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3641365","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}