{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T22:46:26Z","timestamp":1764974786747,"version":"3.46.0"},"reference-count":25,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0116700"],"award-info":[{"award-number":["2022ZD0116700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62033006","62325305"],"award-info":[{"award-number":["62033006","62325305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tac.2025.3587111","type":"journal-article","created":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T13:41:59Z","timestamp":1751982119000},"page":"8414-8421","source":"Crossref","is-referenced-by-count":0,"title":["Policy Gradient Methods for the Cost-Constrained LQR: Strong Duality and Global Convergence"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3142-2903","authenticated-orcid":false,"given":"Feiran","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Automation and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4355-5340","authenticated-orcid":false,"given":"Keyou","family":"You","sequence":"additional","affiliation":[{"name":"Department of Automation and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9467-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21314\/jor.2002.057"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref5","first-page":"7555","article-title":"Constrained reinforcement learning has zero duality gap","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","author":"Paternain","year":"2019"},{"issue":"1","key":"ref6","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref7","first-page":"8378","article-title":"Natural policy gradient primal-dual method for constrained Markov decision processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ding","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794293"},{"key":"ref9","first-page":"3127","article-title":"Convergent policy optimization for safe reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Yu","year":"2019"},{"key":"ref10","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fazel","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2025.3569597"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2024.3409749"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3234176"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/9.774108"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303967"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683474"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431592"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.1983.9753066"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-44184-5_100076"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2024.3455508"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/sj.jors.2600425"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/S0895479895291303"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-009-9522-7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1561\/9781680831719"},{"key":"ref25","first-page":"11598","article-title":"Policy optimization provably converges to Nash equilibria in zero-sum linear quadratic games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2019"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9\/11278429\/11072721.pdf?arnumber=11072721","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T22:42:23Z","timestamp":1764974543000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11072721\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":25,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tac.2025.3587111","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"type":"print","value":"0018-9286"},{"type":"electronic","value":"1558-2523"},{"type":"electronic","value":"2334-3303"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}