{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:24:24Z","timestamp":1781587464332,"version":"3.54.5"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2017,4,1]],"date-time":"2017-04-01T00:00:00Z","timestamp":1491004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada (NSERC)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2017,4]]},"DOI":"10.1109\/tac.2016.2598476","type":"journal-article","created":{"date-parts":[[2016,8,5]],"date-time":"2016-08-05T18:20:14Z","timestamp":1470421214000},"page":"1545-1558","source":"Crossref","is-referenced-by-count":87,"title":["Decentralized Q-Learning for Stochastic Teams and Games"],"prefix":"10.1109","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8295-1509","authenticated-orcid":false,"given":"Gurdal","family":"Arslan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Serdar","family":"Yuksel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2202\/1534-5971.1109"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1214\/aoap\/1069786497","article-title":"Convergent multiple-timescales reinforcement learning algorithms in normal form games","volume":"13","author":"leslie","year":"2003","journal-title":"Ann Appl Probabil"},{"key":"ref33","author":"fudenberg","year":"1998","journal-title":"The Theory of Learning in Games"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012903437976"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199269181.001.0001"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/070680199"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1006\/game.1997.0626"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2009.2017273"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1006\/game.1996.0044"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF01769064"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.geb.2005.08.005"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1142\/S0219525902000535"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"ref13","article-title":"Scalable learning in stochastic games","author":"bowling","year":"0","journal-title":"Proc Workshop Game Theoretic Decision Theoretic Agents"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/S036301299731669X"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1515\/9781400874668"},{"key":"ref16","author":"isaacs","year":"1965","journal-title":"Differential Games"},{"key":"ref17","author":"ba?ar","year":"1995","journal-title":"H-Infinity Optimal Control and Related Minimax Design Problems A Dynamic Game Approach"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/9.286259"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.05.025"},{"key":"ref28","author":"fudenberg","year":"1991","journal-title":"Game Theory"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref27","first-page":"2996","article-title":"Distributed model predictive control as a game with coupled constraints","author":"trodden","year":"0","journal-title":"Proc Eur Control Conf"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2006.02.006"},{"key":"ref6","first-page":"374","article-title":"Iterative solutions of games by fictitious play","author":"brown","year":"1951","journal-title":"Activ Anal Prod Allocat"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16170-4_12"},{"key":"ref5","first-page":"426","article-title":"Learning to coordinate without sharing information","author":"sen","year":"0","journal-title":"Proc 12th Nat Conf Artificial Intelligence"},{"key":"ref8","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"0","journal-title":"Proc 10th Conf on Artificial Intelligence for Applications"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2307\/1969530"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00186-007-0158-9"},{"key":"ref1","first-page":"89","article-title":"Equilibrium in a stochastic $n$-person game","volume":"28","author":"fink","year":"1964","journal-title":"J Sci Hiroshima Univ Ser AII"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2014.2364710"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2010.01.080157"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF01206560"},{"key":"ref42","first-page":"1","article-title":"Learning rates for Q-learning","volume":"5","author":"even-dar","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2007.899732"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1137\/120893501"},{"key":"ref23","first-page":"1059","article-title":"Network security configurations: A nonzero-sum stochastic game approach","author":"zhu","year":"0","journal-title":"Proc American Control Conf"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-7085-4","author":"y\u00fcksel","year":"2013","journal-title":"Stochastic Networked Control Systems Stabilization and Optimization under Information Constraints"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2007.051043"},{"key":"ref25","first-page":"644","article-title":"Team decision theory and information structures","volume":"68","author":"ho","year":"0","journal-title":"Proc IEEE"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/7887774\/07534842.pdf?arnumber=7534842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T15:01:48Z","timestamp":1692457308000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7534842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4]]},"references-count":43,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tac.2016.2598476","relation":{},"ISSN":["0018-9286","1558-2523"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,4]]}}}