{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:05:43Z","timestamp":1784131543898,"version":"3.55.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["CNS-2148309"],"award-info":[{"award-number":["CNS-2148309"]}]},{"name":"NSF","award":["ECCS-2210320"],"award-info":[{"award-number":["ECCS-2210320"]}]},{"name":"ARO","award":["W911NF-24-1-0085"],"award-info":[{"award-number":["W911NF-24-1-0085"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tac.2024.3397928","type":"journal-article","created":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T17:45:08Z","timestamp":1715103908000},"page":"7678-7693","source":"Crossref","is-referenced-by-count":12,"title":["Robust Reinforcement Learning for Risk-Sensitive Linear Quadratic Gaussian Control"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8031-7638","authenticated-orcid":false,"given":"Leilei","family":"Cui","sequence":"first","affiliation":[{"name":"Control and Networks Lab, Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4406-7875","authenticated-orcid":false,"given":"Tamer","family":"Ba\u015far","sequence":"additional","affiliation":[{"name":"Coordinated Science Laboratory, University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4868-9359","authenticated-orcid":false,"given":"Zhong-Ping","family":"Jiang","sequence":"additional","affiliation":[{"name":"Control and Networks Lab, Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3087455"},{"key":"ref3","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Fazel","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3037046"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3128592"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1971.1099755"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1968.1098829"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/9781119132677"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77653-6_3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17122"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3085510"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2022.105138"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1973.1100265"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2307\/1426972"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6911(88)90055-2"},{"key":"ref17","article-title":"$\\mathcal {H}_\\infty$-Optimal Control and Related Minimax Design Problems: A Dynamic Game Approach","author":"Baar","year":"1995"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.09.019"},{"key":"ref19","first-page":"2764","article-title":"Provably efficient actor-critic for risk-sensitive and robust adversarial RL: A linear-quadratic case","volume-title":"Proc. 24th Int. Conf. Artif. Intell. Statist.","author":"Zhang","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/20M1347942"},{"key":"ref21","first-page":"11602","article-title":"Policy optimization provably converges to Nash equilibria in zero-sum linear quadratic games","volume":"32","author":"Zhang","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref22","article-title":"Global convergence of policy gradient for sequential zero-sum linear quadratic dynamic games","author":"Bu","year":"2019"},{"key":"ref23","first-page":"22056","article-title":"On the stability and convergence of robust adversarial reinforcement learning: A case study on linear quadratic systems","volume":"33","author":"Zhang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2006.884959"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.1760"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2024.105804"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1561\/2600000023"},{"key":"ref28","volume-title":"Neuro-Dynamic Programming","author":"Bertsekas","year":"1996"},{"key":"ref29","first-page":"534","article-title":"A reinforcement learning look at risk-sensitive linear quadratic Gaussian control","volume-title":"Proc. 5th Annu. Learn. Dyn. Control Conf.","author":"Cui","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/20m1347942"},{"key":"ref31","volume-title":"Robust and Optimal Control","author":"Zhou","year":"1996"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2018.09.001"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1966.1098316"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-50085-5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(01)00028-0"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-74628-5"},{"key":"ref39","volume-title":"Adaptive Control","author":"strm","year":"2008"},{"key":"ref40","volume-title":"Reinforcement Learning and Approximate Dynamic Programming for Feedback Control","author":"Lewis","year":"2013"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-68829-7","volume-title":"Theory of Probability and Random Processes","author":"Koralov","year":"2007"},{"key":"ref42","volume-title":"Matrix Differential Calculus With Applications in Statistics and Econometrics","author":"Magnus","year":"2007"},{"key":"ref43","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":"Adv. Neural Inf. Process. Syst."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/37.24809"},{"key":"ref45","article-title":"Robust reinforcement learning for risk-sensitive linear quadratic Gaussian control","author":"Cui","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/0022-2496(85)90006-9"},{"key":"ref47","volume-title":"Linear System Theory and Design","author":"Chen","year":"1999"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1986.1104370"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.23943\/9781400890088"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/9\/10736196\/10521710-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10736196\/10521710.pdf?arnumber=10521710","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:12:49Z","timestamp":1732666369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10521710\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":49,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tac.2024.3397928","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":[[2024,11]]}}}