{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T07:09:38Z","timestamp":1766732978274,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T00:00:00Z","timestamp":1652140800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T00:00:00Z","timestamp":1652140800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000181","name":"AFOSR","doi-asserted-by":"crossref","award":["FA9550-19-1-0353"],"award-info":[{"award-number":["FA9550-19-1-0353"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"crossref"}]},{"name":"US ARL Cooperative Agreement","award":["W911NF-17-2-0196"],"award-info":[{"award-number":["W911NF-17-2-0196"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Dyn Games Appl"],"DOI":"10.1007\/s13235-022-00448-w","type":"journal-article","created":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:07:04Z","timestamp":1652198824000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Reinforcement Learning for Non-stationary Discrete-Time Linear\u2013Quadratic Mean-Field Games in Multiple Populations"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7624-7737","authenticated-orcid":false,"given":"Muhammad Aneeq","family":"uz Zaman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erik","family":"Miehling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tamer","family":"Ba\u015far","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,10]]},"reference":[{"issue":"5","key":"448_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00526-020-01816-3","volume":"59","author":"Y Achdou","year":"2020","unstructured":"Achdou Y, Dao M-K, Ley O, Tchou N (2020) Finite horizon mean field games on networks. Calc Var Partial Differ Equ 59(5):1\u201334","journal-title":"Calc Var Partial Differ Equ"},{"unstructured":"Anahtarc\u0131 B, Kar\u0131ks\u0131z CD, Saldi N (2019) Fitted Q-learning in mean-field games. arXiv preprint arXiv:1912.13309","key":"448_CR2"},{"key":"448_CR3","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.sysconle.2017.07.010","volume":"107","author":"D Bauso","year":"2017","unstructured":"Bauso D (2017) Consensus via multi-population robust mean-field games. Syst Control Lett 107:76\u201383","journal-title":"Syst Control Lett"},{"issue":"6","key":"448_CR4","doi-asserted-by":"publisher","first-page":"3225","DOI":"10.1137\/140985676","volume":"54","author":"D Bauso","year":"2016","unstructured":"Bauso D, Tembine H, Ba\u015far T (2016) Opinion dynamics in social networks through mean-field games. SIAM J Control Optim 54(6):3225\u20133257","journal-title":"SIAM J Control Optim"},{"issue":"2","key":"448_CR5","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1007\/s10957-015-0819-4","volume":"169","author":"A Bensoussan","year":"2016","unstructured":"Bensoussan A, Sung K, Yam SCP, Yung S-P (2016) Linear-quadratic mean field games. J Optim Theory Appl 169(2):496\u2013529","journal-title":"J Optim Theory Appl"},{"key":"448_CR6","volume-title":"Applied optimal control, revised printing","author":"AE Bryson","year":"1975","unstructured":"Bryson AE, Ho Y-C (1975) Applied optimal control, revised printing. Hemisphere, New York"},{"doi-asserted-by":"crossref","unstructured":"Caines, PE, Huang M (2019) Graphon mean field games and the GMFG equations: $$\\varepsilon $$-Nash equilibria. In: 2019 IEEE 58th conference on decision and control (CDC), pp 286\u2013292. IEEE","key":"448_CR7","DOI":"10.1109\/CDC40024.2019.9029871"},{"issue":"2","key":"448_CR8","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1137\/15M1022082","volume":"54","author":"F Camilli","year":"2016","unstructured":"Camilli F, Marchi C (2016) Stationary mean field games systems defined on networks. SIAM J Control Optim 54(2):1085\u20131103","journal-title":"SIAM J Control Optim"},{"key":"448_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-56436-4","volume-title":"Probabilistic theory of mean field games with applications I","author":"R Carmona","year":"2018","unstructured":"Carmona R, Delarue F (2018) Probabilistic theory of mean field games with applications I. Springer, Cham"},{"key":"448_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1051\/proc\/201760001","volume":"60","author":"F Delarue","year":"2017","unstructured":"Delarue F (2017) Mean field games: a toy model on an Erd\u00f6s\u2013Renyi graph. ESAIM Proc Surv 60:1\u201326","journal-title":"ESAIM Proc Surv"},{"unstructured":"Elie R, P\u00e9rolat J, Lauri\u00e8re M, Geist M, Pietquin O (2019) Approximate fictitious play for mean field games. arXiv preprint arXiv:1907.02633","key":"448_CR11"},{"unstructured":"Fazel M, Ge R, Kakade SM, Mesbahi M (2018) Global convergence of policy gradient methods for the linear quadratic regulator. In: International conference on machine learning, pp 1467\u20131476","key":"448_CR12"},{"unstructured":"Fu Z, Yang Z, Chen Y, Wang Z (2020) Actor-critic provably finds Nash equilibria of linear-quadratic mean-field games. In: International conference on learning representation","key":"448_CR13"},{"doi-asserted-by":"crossref","unstructured":"Gao S, Caines PE, Huang M (2020) LQG graphon mean field games. arXiv preprint arXiv:2004.00679","key":"448_CR14","DOI":"10.1109\/CDC45484.2021.9683037"},{"issue":"1","key":"448_CR15","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1109\/TCST.2007.899732","volume":"16","author":"D Gu","year":"2007","unstructured":"Gu D (2007) A differential game approach to formation control. IEEE Trans Control Syst Technol 16(1):85\u201393","journal-title":"IEEE Trans Control Syst Technol"},{"unstructured":"Guo X, Hu A, Xu R, Zhang J (2019) Learning mean-field games. In: Advances in neural information processing systems","key":"448_CR16"},{"doi-asserted-by":"crossref","unstructured":"Huang M, Zhou M (2018) Linear quadratic mean field games\u2013Part I: the asymptotic solvability problem. arXiv preprint arXiv:1811.00522","key":"448_CR17","DOI":"10.1109\/CDC40024.2019.9029174"},{"issue":"3","key":"448_CR18","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 RP, Caines PE et al (2006) Large population stochastic dynamic games: Closed-loop Mckean-Vlasov systems and the Nash certainty equivalence principle. Commun Inf Syst 6(3):221\u2013252","journal-title":"Commun Inf Syst"},{"issue":"9","key":"448_CR19","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1109\/TAC.2007.904450","volume":"52","author":"M Huang","year":"2007","unstructured":"Huang M, Caines PE, Malham\u00e9 RP (2007) Large-population cost-coupled LQG problems with nonuniform agents: individual-mass behavior and decentralized $$\\varepsilon $$-Nash equilibria. IEEE Trans Autom Control 52(9):1560\u20131571","journal-title":"IEEE Trans Autom Control"},{"issue":"1","key":"448_CR20","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/s11537-007-0657-8","volume":"2","author":"J-M Lasry","year":"2007","unstructured":"Lasry J-M, Lions P-L (2007) Mean field games. Jpn J Math 2(1):229\u2013260","journal-title":"Jpn J Math"},{"key":"448_CR21","volume-title":"Cooperative control of multi-agent systems: optimal and adaptive design approaches","author":"FL Lewis","year":"2013","unstructured":"Lewis FL, Zhang H, Hengster-Movric K, Das A (2013) Cooperative control of multi-agent systems: optimal and adaptive design approaches. Springer, Berlin"},{"unstructured":"Malik D, Pananjady A, Bhatia K, Khamaru K, Bartlett P, Wainwright M (2019) Derivative-free methods for policy optimization: Guarantees for linear quadratic systems. In: The 22nd international conference on artificial intelligence and statistics, pp 2916\u20132925. PMLR","key":"448_CR22"},{"doi-asserted-by":"crossref","unstructured":"Moon J, Ba\u015far T (2014) Discrete-time LQG mean field games with unreliable communication. In: 53rd IEEE conference on decision and control, pp 2697\u20132702. IEEE","key":"448_CR23","DOI":"10.1109\/CDC.2014.7039802"},{"issue":"6","key":"448_CR24","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":"448_CR25","volume-title":"Introduction to stochastic search and optimization: estimation, simulation, and control","author":"JC Spall","year":"2005","unstructured":"Spall JC (2005) Introduction to stochastic search and optimization: estimation, simulation, and control, vol 65. Wiley, Hoboken"},{"unstructured":"Subramanian J, Mahajan A (2019) Reinforcement learning in stationary mean-field games. In: International conference on autonomous agents and multiagent systems, pp 251\u2013259","key":"448_CR26"},{"unstructured":"Yang Z, Chen Y, Hong M, Wang Z (2019) Provably global convergence of actor-critic: A case for linear quadratic regulator with ergodic cost. In: Advances in neural information processing systems, pp 8351\u20138363","key":"448_CR27"},{"doi-asserted-by":"crossref","unstructured":"Zaman MAu, Zhang K, Miehling E, Ba\u015far T (2020a) Approximate equilibrium computation for discrete-time linear-quadratic mean-field games. In: 2020 American control conference (ACC), pp 333\u2013339. IEEE","key":"448_CR28","DOI":"10.23919\/ACC45564.2020.9147474"},{"doi-asserted-by":"crossref","unstructured":"Zaman MAu, Zhang K, Miehling E, Ba\u015far T (2020b) Reinforcement learning in non-stationary discrete-time linear-quadratic mean-field games. In: 2020 59th IEEE conference on decision and control (CDC), pp 2278\u20132284. IEEE","key":"448_CR29","DOI":"10.1109\/CDC42340.2020.9304279"},{"issue":"12","key":"448_CR30","doi-asserted-by":"publisher","first-page":"2327","DOI":"10.1109\/JPROC.2019.2952892","volume":"107","author":"Y Zeng","year":"2019","unstructured":"Zeng Y, Wu Q, Zhang R (2019) Accessing from the sky: a tutorial on UAV communications for 5G and beyond. Proc IEEE 107(12):2327\u20132375","journal-title":"Proc IEEE"},{"unstructured":"Zhu Q, Ba\u015far T (2011) A multi-resolution large population game framework for smart grid demand response management. In: International conference on network games, control and optimization (NetGCooP 2011), pp 1\u20138. IEEE","key":"448_CR31"}],"container-title":["Dynamic Games and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13235-022-00448-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13235-022-00448-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13235-022-00448-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T08:08:51Z","timestamp":1727165331000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13235-022-00448-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,10]]},"references-count":31,"alternative-id":["448"],"URL":"https:\/\/doi.org\/10.1007\/s13235-022-00448-w","relation":{},"ISSN":["2153-0785","2153-0793"],"issn-type":[{"type":"print","value":"2153-0785"},{"type":"electronic","value":"2153-0793"}],"subject":[],"published":{"date-parts":[[2022,5,10]]},"assertion":[{"value":"6 April 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}