{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T17:42:13Z","timestamp":1772300533656,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"The Scientific and Technological Research Council of Türkiye","award":["2232-B"],"award-info":[{"award-number":["2232-B"]}]},{"name":"International Fellowship for Early Stage Researchers","award":["121C124"],"award-info":[{"award-number":["121C124"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tac.2025.3576039","type":"journal-article","created":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T14:05:18Z","timestamp":1748873118000},"page":"7523-7537","source":"Crossref","is-referenced-by-count":1,"title":["Convergence of Heterogeneous Learning Dynamics in Zero-Sum Stochastic Games"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7516-4850","authenticated-orcid":false,"given":"Yuksel","family":"Arslantas","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronics Engineering, Bilkent University, Ankara, Türkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6765-3598","authenticated-orcid":false,"given":"Ege","family":"Yuceel","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, Bilkent University, Ankara, Türkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7824-4121","authenticated-orcid":false,"given":"Yigit","family":"Yalin","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Bilkent University, Ankara, Türkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5779-3986","authenticated-orcid":false,"given":"Muhammed O.","family":"Sayin","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, Bilkent University, Ankara, Türkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2598476"},{"key":"ref2","first-page":"5527","article-title":"Independent policy gradient methods for competitive reinforcement learning","volume-title":"Proc. Conf. Neural Inf. Process.","author":"Daskalakis","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jet.2020.105095"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/21M1426675"},{"key":"ref5","first-page":"18320","article-title":"Decentralized q-learning in zero-sum Markov games","volume-title":"Proc. Conf. Neural Inform. Process.","author":"Sayin","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3490486.3538289"},{"key":"ref7","first-page":"1","article-title":"Last-iterate convergence of decentralized optimistic gradient descent\/ascent in infinite-horizon competitive Markov games","volume-title":"Proc. 34th Annu. Conf. Learn. Theory","volume":"134","author":"Wei","year":"2021"},{"key":"ref8","first-page":"1664","article-title":"Best-response dynamics and fictitious play in identical interest stochastic games","volume-title":"Proc. Internat. Conf. Mach. Learn.","author":"Baudin","year":"2022"},{"key":"ref9","first-page":"20243","article-title":"Smooth fictitious play in stochastic games with perturbed payoffs and unknown transitions","volume-title":"Proc. Conf. Neural Inform. Process.","author":"Baudin","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.economics.050708.142930"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-7085-4"},{"key":"ref13","first-page":"377","article-title":"Iterated solution of games by fictitious play","volume-title":"Proc. Activity Anal. Production Allocation","author":"Brown","year":"1951"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1006\/game.1993.1021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012903437976"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012904439301"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1287\/11-SSY056"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2307\/1969530"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1006\/game.1997.0582"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.geb.2004.06.006"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1006\/game.1997.0544"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S1094-2025(03)00011-5"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jedc.2006.11.002"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1515\/1558-3708.1899"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1111\/1468-0262.00054"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1006\/jmps.1998.1217"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.geb.2021.11.015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2021.105002"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9993156"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008933826411"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389486"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.920232"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2015.2461213"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341900"},{"key":"ref35","first-page":"17455","article-title":"Cooperative heterogeneous deep reinforcement learning","volume-title":"Proc. Conf. Neural Inform. Process.","author":"Zheng","year":"2020"},{"key":"ref36","first-page":"1656","article-title":"Competitive and cooperative heterogeneous deep reinforcement learning","volume-title":"Proc. Internat. Joint Conf. Auton. Agents Multiagent Syst.","author":"Zheng","year":"2020"},{"key":"ref37","first-page":"1","article-title":"Heterogeneous-agent reinforcement learning","volume":"25","author":"Zhong","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2025.3576379"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1137\/23M1592559"},{"key":"ref40","article-title":"Asymmetric feedback learning in online convex games","author":"Wang","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1214\/aoap\/1069786497"},{"key":"ref42","first-page":"935","article-title":"Convergence analysis of gradient-based learning in continuous games","volume-title":"Proc. 35th Uncertainty Artif. Intell. Conf.","author":"Chasnov"},{"key":"ref43","first-page":"994","article-title":"On the heterogeneity of independent learning dynamics in zero-sum stochastic games","volume-title":"Proc. Learn. Dyn. Control Conf.","author":"Sayin","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5718053"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3308343"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1095"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref48","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":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-93-86279-38-5"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-0262.2002.00440.x"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1889(94)00819-4"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9\/11218261\/11021434.pdf?arnumber=11021434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:28:21Z","timestamp":1769722101000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11021434\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":52,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tac.2025.3576039","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}