{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T04:03:24Z","timestamp":1752984204043,"version":"3.28.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012652","name":"ETH Zurich","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012652","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation (SNSF)","doi-asserted-by":"publisher","award":["200021-207343"],"award-info":[{"award-number":["200021-207343"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10384025","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:36Z","timestamp":1705671516000},"page":"2602-2609","source":"Crossref","is-referenced-by-count":2,"title":["Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity"],"prefix":"10.1109","author":[{"given":"Jiduan","family":"Wu","sequence":"first","affiliation":[{"name":"ETH Zurich,Department of Computer Science,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anas","family":"Barakat","sequence":"additional","affiliation":[{"name":"ETH Zurich,Department of Computer Science,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ilyas","family":"Fatkhullin","sequence":"additional","affiliation":[{"name":"ETH Zurich,Department of Computer Science,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Niao","family":"He","sequence":"additional","affiliation":[{"name":"ETH Zurich,Department of Computer Science,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2949","article-title":"Derivative-free policy optimization for linear risk-sensitive and robust control design: Implicit regularization and sample complexity","volume":"34","author":"Zhang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tac.1987.1104686"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(63)90382-3"},{"key":"ref5","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"International conference on machine learning","author":"Fazel"},{"volume-title":"System Identification","year":"1998","author":"Ljung","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/267460.267481"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1971.1099755"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198537953.001.0001"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2002.806652"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-042230-5.50016-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1099-1239(199601)6:1<1::AID-RNC128>3.0.CO;2-3"},{"key":"ref13","article-title":"$\\mathcal{H}_{\\infty}$-optimal control and related minimax design problems","volume-title":"Springer Book Archive-Mathematics","author":"Ba\u015far","year":"1995"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/20M1347942"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(77)90023-1"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1109\/CDC49753.2023.10384025","volume-title":"Learning zero-sum linear quadratic games with improved sample complexity","author":"Wu","year":"2023"},{"key":"ref17","first-page":"2916","article-title":"Derivative-free methods for policy optimization: Guarantees for linear quadratic systems","volume-title":"The 22nd international conference on artificial intelligence and statistics","author":"Malik"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3006256"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/20M1382386"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/20M1329858"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3087455"},{"key":"ref22","article-title":"Convergence of policy gradient methods for finite-horizon stochastic linear-quadratic control problems","author":"Giegrich","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"A model-free first-order method for linear quadratic regulator with $\\tilde{O}(1\/\\varepsilon)$ sampling complexity","author":"Ju","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"On the global convergence of actor-critic: A case for linear quadratic regulator with ergodic cost","author":"Yang","year":"2019","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.2989683"},{"key":"ref26","article-title":"Global convergence of direct policy search for state-feedback $\\mathcal{H}_{\\infty}$ robust control: A revisit of nonsmooth synthesis with goldstein subdifferential","volume-title":"Thirty-Sixth Conference on Neural Information Processing Systems","author":"Guo","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9682821"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814952"},{"key":"ref29","article-title":"Policy gradient finds global optimum of nearly linear-quadratic control systems","volume-title":"OPT 2022: Optimization for Machine Learning (NeurIPS 2022 Workshop)","author":"Han","year":"2022"},{"key":"ref30","article-title":"Policy optimization provably converges to nash equilibria in zero-sum linear quadratic games","volume":"32","author":"Zhang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"Global convergence of policy gradient for sequential zero-sum linear quadratic dynamic games","author":"Bu","year":"2019","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2007.7068263"},{"key":"ref33","article-title":"Linear-quadratic zero-sum mean-field type games: Optimality conditions and policy optimization","author":"Carmona","year":"2020","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Linear-quadratic mean-field reinforcement learning: Convergence of policy gradient methods","author":"Carmona","year":"2019","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Policy-gradient algorithms have no guarantees of convergence in linear quadratic games","author":"Mazumdar","year":"2019","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Policy gradient methods find the nash equilibrium in n-player general-sum linear-quadratic games","author":"Hambly","year":"2022","journal-title":"arXiv preprint"},{"volume-title":"Policy gradient methods for linear quadratic problems","year":"2022","author":"Yang","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147358"},{"key":"ref39","article-title":"Online convex optimization in the bandit setting: gradient descent without a gradient","author":"Flaxman","year":"2004","journal-title":"arXiv preprint cs\/0408007"},{"key":"ref40","first-page":"28","article-title":"Optimal algorithms for online convex optimization with multi-point bandit feedback","volume-title":"Colt","author":"Agarwal","year":"2010"},{"key":"ref41","first-page":"6083","article-title":"On gradient descent ascent for nonconvex-concave minimax problems","volume-title":"International Conference on Machine Learning","author":"Lin"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1137\/0326018"},{"key":"ref43","article-title":"Policy gradient converges to the globally optimal policy for nearly linear-quadratic regulators","author":"Han","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2023,12,13]]},"location":"Singapore, Singapore","end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10384025.pdf?arnumber=10384025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T11:35:14Z","timestamp":1706009714000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10384025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10384025","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}