{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:27:36Z","timestamp":1777501656729,"version":"3.51.4"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["2022YFB2502901"],"award-info":[{"award-number":["2022YFB2502901"]}]},{"name":"Tsinghua University-Toyota Joint Research Center for AI Technology of Automated Vehicle"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52202487"],"award-info":[{"award-number":["52202487"]}],"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":[[2024,1]]},"DOI":"10.1109\/tac.2023.3266277","type":"journal-article","created":{"date-parts":[[2023,4,11]],"date-time":"2023-04-11T17:35:17Z","timestamp":1681234517000},"page":"426-433","source":"Crossref","is-referenced-by-count":24,"title":["Relaxed Policy Iteration Algorithm for Nonlinear Zero-Sum Games With Application to H-Infinity Control"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3718-5593","authenticated-orcid":false,"given":"Jie","family":"Li","sequence":"first","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4923-3633","authenticated-orcid":false,"given":"Shengbo Eben","family":"Li","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3697-1576","authenticated-orcid":false,"given":"Jingliang","family":"Duan","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1539-472X","authenticated-orcid":false,"given":"Yao","family":"Lyu","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5331-0938","authenticated-orcid":false,"given":"Wenjun","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0689-0510","authenticated-orcid":false,"given":"Yang","family":"Guan","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2854-921X","authenticated-orcid":false,"given":"Yuming","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4757-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1981.1102603"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF01211560"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/9.256331"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/9.159566"},{"key":"ref6","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50815-3"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejcon.2013.05.017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2712188"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2006.884959"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2000204"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2012.2217349"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2441749"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5717676"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2653800"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2643687"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.11.021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2013.2284545"},{"key":"ref19","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.10.033"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5717148"},{"key":"ref23","volume-title":"Functional Analysis","author":"Kantorovich","year":"1982"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.2997559"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.06.022"},{"key":"ref26","first-page":"1861","article-title":"Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.134"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10376321\/10098871.pdf?arnumber=10098871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T19:47:46Z","timestamp":1735847266000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10098871\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":28,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tac.2023.3266277","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}