{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T16:41:34Z","timestamp":1772296894931,"version":"3.50.1"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12,14]]},"DOI":"10.1109\/cdc42340.2020.9303734","type":"proceedings-article","created":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T07:27:32Z","timestamp":1610522852000},"page":"1038-1043","source":"Crossref","is-referenced-by-count":6,"title":["Policy Optimization for Linear-Quadratic Zero-Sum Mean-Field Type Games"],"prefix":"10.1109","author":[{"given":"Rene","family":"Carmona","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenza","family":"Hamidouche","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathieu","family":"Lauriere","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongjun","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.09.019"},{"key":"ref11","article-title":"Linear-quadratic mean-field reinforcement learning: convergence of policy gradient methods","author":"carmona","year":"2019"},{"key":"ref12","article-title":"Model-free mean-field reinforcement learning: mean-field mdp and mean-field q-learning","author":"carmona","year":"2019"},{"key":"ref13","first-page":"11 598","article-title":"Policy optimization provably converges to nash equilibria in zero-sum linear quadratic games","author":"zhang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Linear-Quadratic Zero-Sum Mean-Field Type Games: Optimality Conditions and Policy Optimization","author":"carmona","year":"2020"},{"key":"ref15","article-title":"Mean field control and mean field game models with several populations","author":"bensoussan","year":"2018"},{"key":"ref16","article-title":"Mean-field-type games in engineering","author":"djehiche","year":"2016"},{"key":"ref17","volume":"83","author":"carmona","year":"2018","journal-title":"Probabilistic Theory of Mean Field Games with Applications I"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"108647","DOI":"10.1016\/j.automatica.2019.108647","article-title":"Discrete-time linear-quadratic mean-field-type repeated games: Perfect, incomplete, and imperfect information","volume":"112","author":"barreiro-gomez","year":"2020","journal-title":"Automatica"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-8176-4581-6","author":"bensoussan","year":"2007","journal-title":"Representation and Control of Infinite Dimensional Systems"},{"key":"ref6","first-page":"1651","article-title":"Zero-sum stochastic differential games of mean-field type and bsdes","author":"xu","year":"2012","journal-title":"Proceedings of the 31st Chinese Control Conference"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4757-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s00245-018-9525-6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpur.2018.12.005"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"221","DOI":"10.4310\/CIS.2006.v6.n3.a5","article-title":"Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle","volume":"6","author":"huang","year":"2006","journal-title":"Commun Inf Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11537-007-0657-8"},{"key":"ref9","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","author":"fazel","year":"2018"}],"event":{"name":"2020 59th IEEE Conference on Decision and Control (CDC)","location":"Jeju, Korea (South)","start":{"date-parts":[[2020,12,14]]},"end":{"date-parts":[[2020,12,18]]}},"container-title":["2020 59th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9303728\/9303729\/09303734.pdf?arnumber=9303734","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:59:11Z","timestamp":1656345551000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9303734\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,14]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/cdc42340.2020.9303734","relation":{},"subject":[],"published":{"date-parts":[[2020,12,14]]}}}