{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:46:23Z","timestamp":1768340783470,"version":"3.49.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100008967","name":"Bilim Akademisi","doi-asserted-by":"publisher","award":["BAGEP 2021"],"award-info":[{"award-number":["BAGEP 2021"]}],"id":[{"id":"10.13039\/501100008967","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Dyn Games Appl"],"DOI":"10.1007\/s13235-022-00450-2","type":"journal-article","created":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T19:05:35Z","timestamp":1653332735000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Q-Learning in Regularized Mean-field Games"],"prefix":"10.1007","author":[{"given":"Berkay","family":"Anahtarci","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Can Deha","family":"Kariksiz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2677-7366","authenticated-orcid":false,"given":"Naci","family":"Saldi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,23]]},"reference":[{"key":"450_CR1","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1016\/j.jet.2013.07.002","volume":"156","author":"S Adlakha","year":"2015","unstructured":"Adlakha S, Johari R, Weintraub G (2015) Equilibria of dynamic games with many players: existence, approximation, and market structure. J Econ Theory 156:269\u2013316","journal-title":"J Econ Theory"},{"key":"450_CR2","unstructured":"Anahtarci B, Kariksiz C, Saldi N (2019) Fitted Q-learning in mean-field games. arXiv:1912.13309"},{"key":"450_CR3","doi-asserted-by":"crossref","unstructured":"Anahtarci B, Kariksiz C, Saldi N (2020) Value iteration algorithm for mean field games. Syst Control Lett 143","DOI":"10.1016\/j.sysconle.2020.104744"},{"key":"450_CR4","unstructured":"Antos A, Munos R, Szepesv\u00e1ri C (2007) Fitted Q-iteration in continuous action-space MDPs. In: Proceedings of the 20th international conference on neural information processing systems, pp 9\u201316"},{"key":"450_CR5","unstructured":"Antos A, Munos R, Szepesv\u00e1ri C (2007) Fitted Q-iteration in continuous action-space MDPs. Tech. rep. inria-00185311v1"},{"key":"450_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-8508-7","volume-title":"Mean field games and mean field type control theory","author":"A Bensoussan","year":"2013","unstructured":"Bensoussan A, Frehse J, Yam P (2013) Mean field games and mean field type control theory. Springer, New York"},{"key":"450_CR7","unstructured":"Biswas A (2015) Mean field games with ergodic cost for discrete time Markov processes. arXiv:1510.08968"},{"key":"450_CR8","unstructured":"Cardaliaguet P (2011) Notes on mean-field games. Technical report, p 120"},{"issue":"4","key":"450_CR9","doi-asserted-by":"publisher","first-page":"2705","DOI":"10.1137\/120883499","volume":"51","author":"R Carmona","year":"2013","unstructured":"Carmona R, Delarue F (2013) Probabilistic analysis of mean-field games. SIAM J Control Optim 51(4):2705\u20132734","journal-title":"SIAM J Control Optim"},{"key":"450_CR10","unstructured":"Carmona R, Lauriere M, Tan Z (2019) Linear-quadratic mean-field reinforcement learning: convergence of policy gradient methods. arXiv:1910.04295"},{"key":"450_CR11","unstructured":"Elie R, Perolat J, Lauriere M, Geist M, Pietquin O (2019) Approximate fictitious play for mean-field games. arXiv:1907.02633"},{"key":"450_CR12","doi-asserted-by":"publisher","first-page":"3222","DOI":"10.1016\/j.automatica.2013.08.017","volume":"49","author":"R Elliot","year":"2013","unstructured":"Elliot R, Li X, Ni Y (2013) Discrete time mean-field stochastic linear-quadratic optimal control problems. Automatica 49:3222\u20133233","journal-title":"Automatica"},{"key":"450_CR13","unstructured":"Fu Z, Yang Z, Chen Y, Wang Z (2019) Actor-critic provably finds Nash equilibria of linear-quadratic mean-field games. arXiv:1910.07498"},{"key":"450_CR14","unstructured":"Geist M, Scherrer B, Pietquin O (2019) A theory of regularized Markov decision processes. arXiv:1901.11275"},{"key":"450_CR15","doi-asserted-by":"crossref","unstructured":"Georgii H (2011) Gibbs Measures and Phase Transitions. De Gruyter studies in mathematics. De Gruyter","DOI":"10.1515\/9783110250329"},{"key":"450_CR16","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1016\/j.matpur.2009.10.010","volume":"93","author":"D Gomes","year":"2010","unstructured":"Gomes D, Mohr J, Souza R (2010) Discrete time, finite state space mean field games. J Math Pures Appl 93:308\u2013328","journal-title":"J Math Pures Appl"},{"issue":"2","key":"450_CR17","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1007\/s13235-013-0099-2","volume":"4","author":"D Gomes","year":"2014","unstructured":"Gomes D, Sa\u00fade J (2014) Mean field games models: a brief survey. Dyn Games Appl 4(2):110\u2013154","journal-title":"Dyn Games Appl"},{"key":"450_CR18","unstructured":"Guo X, Hu A, Xu R, Zhang J (2019) Learning mean-field games. arXiv:1901.09585"},{"issue":"5","key":"450_CR19","doi-asserted-by":"publisher","first-page":"3318","DOI":"10.1137\/080735370","volume":"48","author":"M Huang","year":"2010","unstructured":"Huang M (2010) Large-population LQG games involving major player: the nash certainty equivalence principle. SIAM J Control Optim 48(5):3318\u20133353","journal-title":"SIAM J Control Optim"},{"issue":"9","key":"450_CR20","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1109\/TAC.2007.904450","volume":"52","author":"M Huang","year":"2007","unstructured":"Huang M, Caines P, Malham\u00e9 R (2007) Large-population cost coupled LQG problems with nonuniform agents: individual-mass behavior and decentralized $$\\epsilon $$-Nash equilibria. IEEE Trans Autom Control 52(9):1560\u20131571","journal-title":"IEEE Trans Autom Control"},{"key":"450_CR21","doi-asserted-by":"publisher","first-page":"221","DOI":"10.4310\/CIS.2006.v6.n3.a5","volume":"6","author":"M Huang","year":"2006","unstructured":"Huang M, Malham\u00e9 R, Caines P (2006) Large population stochastic dynamic games: closed loop McKean-Vlasov systems and the Nash certainty equivalence principle. Commun Inform Syst 6:221\u2013252","journal-title":"Commun Inform Syst"},{"issue":"3","key":"450_CR22","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1137\/17M1157660","volume":"57","author":"AD Kara","year":"2019","unstructured":"Kara AD, Y\u00fcksel S (2019) Robustness to incorrect priors in partially observed stochastic control. SIAM J Control Optim 57(3):1929\u20131964","journal-title":"SIAM J Control Optim"},{"issue":"2","key":"450_CR23","doi-asserted-by":"publisher","first-page":"1144","DOI":"10.1137\/18M1208058","volume":"58","author":"AD Kara","year":"2020","unstructured":"Kara AD, Y\u00fcksel S (2020) Robustness to incorrect system models in stochastic control. SIAM J Control Optim 58(2):1144\u20131182","journal-title":"SIAM J Control Optim"},{"issue":"6","key":"450_CR24","doi-asserted-by":"publisher","first-page":"2126","DOI":"10.1214\/07-AOP384","volume":"36","author":"L Kontorovich","year":"2008","unstructured":"Kontorovich L, Ramanan K (2008) Concentration inequalities for dependent random variables via the martingale method. Ann Probab 36(6):2126\u20132158","journal-title":"Ann Probab"},{"key":"450_CR25","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/s11537-007-0657-8","volume":"2","author":"J Lasry","year":"2007","unstructured":"Lasry J, Lions P (2007) Mean field games. Japan J Math 2:229\u2013260","journal-title":"Japan J Math"},{"key":"450_CR26","doi-asserted-by":"crossref","unstructured":"Mehta P, Meyn S (2009) Q-learning and Pontryagin\u2019s minimum principle. In: Proceedings of the 48h IEEE Conference on Decision and Control (CDC) held jointly with 2009 28th Chinese Control Conference, pp 3598\u20133605","DOI":"10.1109\/CDC.2009.5399753"},{"key":"450_CR27","doi-asserted-by":"crossref","unstructured":"Moon J, Ba\u015far T (2015) Discrete-time decentralized control using the risk-sensitive performance criterion in the large population regime: a mean field approach. In: ACC 2015. Chicago","DOI":"10.1109\/ACC.2015.7172082"},{"key":"450_CR28","doi-asserted-by":"crossref","unstructured":"Moon J, Ba\u015far T (2016) Discrete-time mean field Stackelberg games with a large number of followers. In: CDC 2016. Las Vegas","DOI":"10.1109\/CDC.2016.7798807"},{"issue":"7","key":"450_CR29","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1080\/00207179.2015.1129560","volume":"89","author":"J Moon","year":"2016","unstructured":"Moon J, Ba\u015far T (2016) Robust mean field games for coupled Markov jump linear systems. Int J Control 89(7):1367\u20131381","journal-title":"Int J Control"},{"key":"450_CR30","unstructured":"Neu G, Jonsson A, Gomez V (2017) A unified view of entropy-regularized Markov decision processes. arXiv:1705.07798"},{"key":"450_CR31","doi-asserted-by":"crossref","unstructured":"Nourian M, Nair G (2013) Linear-quadratic-Gaussian mean field games under high rate quantization. In: CDC 2013. Florence","DOI":"10.1109\/CDC.2013.6760159"},{"key":"450_CR32","unstructured":"Saldi N (2019) Discrete-time average-cost mean-field games on Polish spaces. arXiv:1908.08793 (accepted to Turkish Journal of Mathematics)"},{"issue":"6","key":"450_CR33","doi-asserted-by":"publisher","first-page":"4256","DOI":"10.1137\/17M1112583","volume":"56","author":"N Saldi","year":"2018","unstructured":"Saldi N, Ba\u015far T, Raginsky M (2018) Markov-Nash equilibria in mean-field games with discounted cost. SIAM J Control Optim 56(6):4256\u20134287","journal-title":"SIAM J Control Optim"},{"key":"450_CR34","doi-asserted-by":"crossref","unstructured":"Saldi N, Ba\u015far T, Raginsky M (2019) Approximate Markov-Nash equilibria for discrete-time risk-sensitive mean-field games. to appear in Mathematics of Operations Research","DOI":"10.1109\/CDC40024.2019.9029343"},{"issue":"3","key":"450_CR35","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.1287\/moor.2018.0957","volume":"44","author":"N Saldi","year":"2019","unstructured":"Saldi N, Ba\u015far T, Raginsky M (2019) Approximate Nash equilibria in partially observed stochastic games with mean-field interactions. Math Oper Res 44(3):1006\u20131033","journal-title":"Math Oper Res"},{"key":"450_CR36","unstructured":"Shalev-Shwartz S (2007) Online learning: theory, algorithms, and applications. Ph.D. thesis, The Hebrew University of Jerusalem"},{"issue":"4","key":"450_CR37","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1109\/TAC.2013.2289711","volume":"59","author":"H Tembine","year":"2014","unstructured":"Tembine H, Zhu Q, Ba\u015far T (2014) Risk-sensitive mean field games. IEEE Trans Autom Control 59(4):835\u2013850","journal-title":"IEEE Trans Autom Control"},{"key":"450_CR38","volume-title":"Learning and generalization: with applications to neural networks","author":"M Vidyasagar","year":"2010","unstructured":"Vidyasagar M (2010) Learning and generalization: with applications to neural networks, 2nd edn. Springer, New York","edition":"2"},{"key":"450_CR39","doi-asserted-by":"crossref","unstructured":"Wiecek P (2020) Discrete-time ergodic mean-field games with average reward on compact spaces. Dyn Games Appl 10:222\u2013256","DOI":"10.1007\/s13235-019-00296-1"},{"issue":"2","key":"450_CR40","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1007\/s10957-014-0649-9","volume":"166","author":"P Wiecek","year":"2015","unstructured":"Wiecek P, Altman E (2015) Stationary anonymous sequential games with undiscounted rewards. J Optim Theory Appl 166(2):686\u2013710","journal-title":"J Optim Theory Appl"},{"key":"450_CR41","unstructured":"Yang J, Ye X, Trivedi R, Hu X, Zha H (2018) Learning deep mean field games for modelling large population behaviour. arXiv:1711.03156"},{"key":"450_CR42","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1109\/TAC.2013.2287733","volume":"59","author":"H Yin","year":"2014","unstructured":"Yin H, Mehta P, Meyn S, Shanbhag U (2014) Learning in mean-field games. IEEE Trans Autom Control 59:629\u2013644","journal-title":"IEEE Trans Autom Control"}],"container-title":["Dynamic Games and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13235-022-00450-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13235-022-00450-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13235-022-00450-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T19:22:31Z","timestamp":1653333751000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13235-022-00450-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":42,"alternative-id":["450"],"URL":"https:\/\/doi.org\/10.1007\/s13235-022-00450-2","relation":{},"ISSN":["2153-0785","2153-0793"],"issn-type":[{"value":"2153-0785","type":"print"},{"value":"2153-0793","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,23]]},"assertion":[{"value":"24 April 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}