{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T18:11:35Z","timestamp":1757700695461,"version":"3.37.3"},"reference-count":20,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-16-1-0022"],"award-info":[{"award-number":["FA9550-16-1-0022"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency Lagrange Grant","doi-asserted-by":"publisher","award":["FA8650-18-2-7836"],"award-info":[{"award-number":["FA8650-18-2-7836"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Control Syst. Lett."],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1109\/lcsys.2020.2989683","type":"journal-article","created":{"date-parts":[[2020,4,22]],"date-time":"2020-04-22T20:46:57Z","timestamp":1587588417000},"page":"638-643","source":"Crossref","is-referenced-by-count":7,"title":["Global Convergence of Policy Gradient Algorithms for Indefinite Least Squares Stationary Optimal Control"],"prefix":"10.1109","volume":"4","author":[{"given":"Jingjing","family":"Bu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehran","family":"Mesbahi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref11","first-page":"76","article-title":"Reinforcement learning and feedback control: Using natural decision methods to design optimal adaptive controllers","volume":"32","author":"lewis","year":"2012","journal-title":"IEEE Circuits Syst Mag"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2015.1079737"},{"key":"ref13","volume":"2","author":"bertsekas","year":"2012","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718768"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"ref16","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","author":"fazel","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"article-title":"LQR through the lens of first order methods: Discrete-time case","year":"2019","author":"bu","key":"ref17"},{"journal-title":"Principles of Mathematical Analysis","year":"1976","author":"rudin","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/130912839"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198537953.001.0001","author":"lancaster","year":"1995","journal-title":"Algebraic Riccati Equations"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1971.1099755"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.096"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2002.806652"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2884649"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1971.1099831"},{"key":"ref1","first-page":"102","article-title":"Contributions to the theory of optimal control","volume":"5","author":"kalman","year":"1960","journal-title":"Boletin Sociedad Matemática Mexicana"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1994.735224"},{"article-title":"Global convergence of policy gradient for sequential zero-sum linear quadratic dynamic games","year":"2019","author":"bu","key":"ref20"}],"container-title":["IEEE Control Systems Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782633\/8995821\/09076327.pdf?arnumber=9076327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,4]],"date-time":"2024-08-04T13:22:09Z","timestamp":1722777729000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9076327\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":20,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lcsys.2020.2989683","relation":{},"ISSN":["2475-1456"],"issn-type":[{"type":"electronic","value":"2475-1456"}],"subject":[],"published":{"date-parts":[[2020,7]]}}}