{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T10:09:57Z","timestamp":1775210997697,"version":"3.50.1"},"reference-count":58,"publisher":"Institute for Operations Research and the Management Sciences (INFORMS)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Mathematics of OR"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:p>In this paper, we investigate the robustness of stationary mean-field equilibria in the presence of model uncertainties, specifically focusing on infinite-horizon discounted cost functions. To achieve this, we initially establish convergence conditions for value iteration-based algorithms in mean-field games. Subsequently, utilizing these results, we demonstrate that the mean-field equilibrium obtained through this value iteration algorithm remains robust even in the face of system dynamics misspecifications. We then apply these robustness findings to the finite model approximation problem in mean-field games, showing that if the state space quantization is fine enough, the mean-field equilibrium for the finite model closely approximates the nominal one.<\/jats:p>","DOI":"10.1287\/moor.2023.0316","type":"journal-article","created":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T11:10:16Z","timestamp":1738235416000},"page":"185-217","source":"Crossref","is-referenced-by-count":2,"title":["Robustness and Approximation of Discrete-Time Mean-Field Games Under Discounted Cost Criterion"],"prefix":"10.1287","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0499-9221","authenticated-orcid":false,"given":"U\u011fur","family":"Aydin","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Illinois, Urbana, Illinois 61801"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2677-7366","authenticated-orcid":false,"given":"Naci","family":"Saldi","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Bilkent University, \u00c7ankaya, Ankara 06800, Turkey"}]}],"member":"109","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1137\/090758477"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1137\/100790069"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jet.2013.07.002"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1007\/s13235-016-0203-5"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2020.104744"},{"issue":"17","key":"B6","first-page":"1","volume":"24","author":"Anahtarci B","year":"2023","journal-title":"J. Machine Learn. Res."},{"issue":"1","key":"B7","first-page":"89","volume":"13","author":"Anahtarci B","year":"2023","journal-title":"Dynam. Games Appl."},{"key":"B8","doi-asserted-by":"crossref","unstructured":"Baker G, Y\u00fcksel S (2016) Continuity and robustness to incorrect priors in estimation and control. Guill\u00e9n i F\u00e0bregas A, Mart\u00ednez A, Verd\u00fa S, eds.\n                      2016 IEEE Internat. Sympos. Inform. Theory (ISIT)\n                      (IEEE, Piscataway, NJ), 1999\u20132003.","DOI":"10.1109\/ISIT.2016.7541649"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1007\/s13235-015-0160-4"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-8508-7"},{"key":"B11","volume-title":"Stochastic Optimal Control. Mathematics in Science and Engineering","volume":"139","author":"Bertsekas DP","year":"1978"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316962"},{"key":"B13","unstructured":"Biswas A (2015) Mean field games with ergodic cost for discrete time Markov processes. Preprint, submitted October 30, https:\/\/arxiv.org\/abs\/1510.08968."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-34514-5"},{"key":"B15","volume-title":"\u0393-Convergence for Beginners. Oxford Lecture Series in Mathematics and Its Applications","volume":"22","author":"Braides A","year":"2002"},{"key":"B16","unstructured":"Cardaliaguet P (2011) Notes on mean-field games. Working paper, Universit\u00e9 Paris-Dauphine, Paris."},{"key":"B17","volume-title":"The Master Equation and the Convergence Problem in Mean Field Games","author":"Cardaliaguet P","year":"2019"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1137\/120883499"},{"key":"B19","unstructured":"Cui K, Koeppl H (2021) Approximately solving mean field games via entropy-regularized deep reinforcement learning. Arindam B, Kenji F, eds.\n                      Proc. 24th Internat. Conf. Artificial Intelligence Statist.\n                      , vol. 130 (PMLR, New York), 1909\u20131917."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.08.017"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1007\/s13235-013-0099-2"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11456-4_26"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1274"},{"key":"B24","volume-title":"Discrete-Time Markov Control Processes: Basic Optimality Criteria.","volume":"30","author":"Hern\u00e1ndez-Lerma O","year":"2012"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1137\/080735370"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-25498-8_13"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2007.904450"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.4310\/CIS.2006.v6.n3.a5"},{"key":"B29","unstructured":"Jusup M, P\u00e1sztor B, Janik T, Zhang K, Corman F, Krause A, Bogunovic I (2023) Safe model-based multi-agent mean-field reinforcement learning. Preprint, submitted June 29, https:\/\/arxiv.org\/abs\/2306.17052."},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1137\/17M1157660"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1287\/moor.6.4.493"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1007\/s11537-007-0657-8"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1090\/psapm\/078\/06"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1287\/moor.10.4.619"},{"key":"B35","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. Astolfi A, ed.\n                      2015 Amer. Control Conf. (ACC)\n                      (IEEE, Piscataway, NJ), 4779\u20134784.","DOI":"10.1109\/ACC.2015.7172082"},{"key":"B36","doi-asserted-by":"crossref","unstructured":"Moon J, Ba\u015far T (2016) Discrete-time mean field Stackelberg games with a large number of followers.\n                      Proc. 55th IEEE Conf. Decision Control (CDC \u201816)\n                      (IEEE, Piscataway, NJ), 3578\u20133583.","DOI":"10.1109\/CDC.2016.7798807"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2015.1129560"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2579264"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1050.0216"},{"key":"B40","doi-asserted-by":"crossref","unstructured":"Nourian M, Nair GN (2013) Linear-quadratic-Gaussian mean field games under high rate quantization.\n                      52nd IEEE Conf. Decision Control\n                      (IEEE, Piscataway, NJ), 1898\u20131903.","DOI":"10.1109\/CDC.2013.6760159"},{"key":"B41","author":"P\u00e1sztor B","year":"2023","journal-title":"Trans. Machine Learn. Res."},{"issue":"2","key":"B42","first-page":"463","volume":"44","author":"Saldi N","year":"2020","journal-title":"Turkish J. Math."},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1137\/17M1112583"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2018.0957"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2019.1044"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1007\/s13235-022-00453-z"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2016.0832"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1287\/opre.21.3.728"},{"issue":"3","key":"B49","first-page":"380","volume":"44","author":"Serfozo R","year":"1982","journal-title":"Sankhy\u0101 Ser. A"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1287\/moor.4.1.15"},{"key":"B51","doi-asserted-by":"crossref","unstructured":"Subramanian J, Mahajan A (2019) Reinforcement learning in stationary mean-field games. Elkind E, Veloso M, Agmon N, Taylor ME, eds.\n                      Proc. 18th Internat. Conf. Autonomous Agents MultiAgent Systems\n                      (International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC), 251\u2013259.","DOI":"10.65109\/JVKR7103"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2289711"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71050-9"},{"key":"B54","unstructured":"Weintraub GY, Benkard L, Van Roy B (2005) Oblivious equilibrium: A mean field approximation for large-scale dynamic games. Weiss Y, Sch\u00f6lkopf B, Platt J, eds.\n                      Adv. Neural Inform. Processing Systems 18 (NIPS 2005)\n                      , 1489\u20131496."},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.3982\/ECTA6158"},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.1007\/s13235-019-00296-1"},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-014-0649-9"},{"key":"B58","unstructured":"Zaman MAU, Koppel A, Bhatt S, Ba\u015far T (2023) Oracle-free reinforcement learning in mean-field games along a single sample path. Ruiz F, Dy J, van de Meent J-W, eds.\n                      Internat. Conf. Artificial Intelligence Statist.\n                      , vol. 206 (PMLR, New York), 10178\u201310206."}],"container-title":["Mathematics of Operations Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubsonline.informs.org\/doi\/pdf\/10.1287\/moor.2023.0316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T09:40:47Z","timestamp":1772876447000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubsonline.informs.org\/doi\/10.1287\/moor.2023.0316"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":58,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1287\/moor.2023.0316"],"URL":"https:\/\/doi.org\/10.1287\/moor.2023.0316","relation":{},"ISSN":["0364-765X","1526-5471"],"issn-type":[{"value":"0364-765X","type":"print"},{"value":"1526-5471","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}