{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T15:57:32Z","timestamp":1793289452894,"version":"4.5.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"NSF","award":["ECCS 19-32735"],"award-info":[{"award-number":["ECCS 19-32735"]}]},{"name":"NSF","award":["CAREER-2048168"],"award-info":[{"award-number":["CAREER-2048168"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1109\/tac.2022.3176439","type":"journal-article","created":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T15:31:19Z","timestamp":1653060679000},"page":"2475-2482","source":"Crossref","is-referenced-by-count":15,"title":["Policy Optimization for Markovian Jump Linear Quadratic Control: Gradient Method and Global Convergence"],"prefix":"10.1109","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0173-6805","authenticated-orcid":false,"given":"Joao Paulo","family":"Jansch-Porto","sequence":"first","affiliation":[{"name":"Department of Mechanical Science and Engineering, University of Illinois Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5632-7737","authenticated-orcid":false,"given":"Bin","family":"Hu","sequence":"additional","affiliation":[{"name":"Coordinated Science Laboratory (CSL), Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0596-6050","authenticated-orcid":false,"given":"Geir E.","family":"Dullerud","sequence":"additional","affiliation":[{"name":"Coordinated Science Laboratory (CSL), Department of Mechanical Science and Engineering, University of Illinois Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref2","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Schulman","year":"2015"},{"issue":"1","key":"ref3","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref4","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duan","year":"2016"},{"key":"ref5","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton","year":"2000"},{"key":"ref6","first-page":"1531","article-title":"A natural policy gradient","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kakade","year":"2002"},{"key":"ref7","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref9","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref11","first-page":"6550","article-title":"Towards generalization and simplicity in continuous control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rajeswaran","year":"2017"},{"key":"ref12","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":"ref13","article-title":"LQR through the lens of first order methods: Discrete-time case","author":"Bu","year":"2019"},{"key":"ref14","article-title":"Derivative-free methods for policy optimization: Guarantees for linear quadratic systems","author":"Malik","year":"2018"},{"key":"ref15","article-title":"The gap between model-based and model-free methods on the linear quadratic regulator: An asymptotic viewpoint","author":"Tu","year":"2018"},{"key":"ref16","article-title":"On the global convergence of actor-critic: A case for linear quadratic regulator with ergodic cost","author":"Yang","year":"2019"},{"key":"ref17","first-page":"8512","article-title":"Finite-time analysis of approximate policy iteration for the linear quadratic regulator","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krauth","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3087455"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029985"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/20M1329858"},{"key":"ref21","first-page":"287","article-title":"Learning the globally optimal distributed LQ regulator","volume-title":"Proc. Learn. Dyn. Control","author":"Furieri","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3128592"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/20m1347942"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3037046"},{"key":"ref25","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683735"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/b138575"},{"key":"ref28","volume-title":"Estimation and Tracking- Principles, Techniques, and Software","author":"Bar-Shalom","year":"1993"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2010.2102756"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798654"},{"key":"ref31","article-title":"Learning switching linear models of human motion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pavlovic","year":"2000"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546150"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.2911"},{"key":"ref34","first-page":"1157","article-title":"A unified analysis of stochastic optimization methods using jump system theory and quadratic constraints","volume-title":"Proc. Conf. Learn. Theory","author":"Hu","year":"2017"},{"key":"ref35","first-page":"8477","article-title":"Characterizing the exact behaviors of temporal difference learning algorithms using Markov jump linear system theory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(01)00215-1"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619310"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029946"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1002\/jnm.1981"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147571"},{"key":"ref41","article-title":"Global convergence using policy gradient methods for model-free Markovian jump linear quadratic control","author":"Rathod","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1029-0"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1080\/00207728908910331"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2009.5400233"},{"key":"ref45","volume-title":"Convex Optimization & Euclidean Distance Geometry","author":"Dattorro","year":"2010"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9467-7"},{"key":"ref47","first-page":"947","article-title":"Policy learning of MDPs with mixed continuous\/discrete variables: A case study on model-free control of Markovian jump systems","volume-title":"Proc. 2nd Conf. Learn. Dyn. Control","author":"Jansch-Porto","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/9.544005"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718768"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/9\/10084346\/9779410-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10084346\/09779410.pdf?arnumber=9779410","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T17:21:49Z","timestamp":1705944109000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9779410\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":50,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tac.2022.3176439","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":[[2023,4]]}}}