{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:54:45Z","timestamp":1778349285132,"version":"3.51.4"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011283","name":"State Key Laboratory of Automotive Safety and Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011283","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,6]]},"DOI":"10.1109\/cdc51059.2022.9992503","type":"proceedings-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:26:56Z","timestamp":1673378816000},"page":"4040-4045","source":"Crossref","is-referenced-by-count":4,"title":["On the Optimization Landscape of Dynamic Output Feedback: A Case Study for Linear Quadratic Regulator"],"prefix":"10.1109","author":[{"given":"Jingliang","family":"Duan","sequence":"first","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhan","family":"Cao","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zheng","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Zhao","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2019.00120"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04301-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330668"},{"key":"ref5","article-title":"Continuous control with deep reinforcement learning","volume-title":"4th International Conference on Learning Representations (ICLR 2016)","author":"Lillicrap"},{"key":"ref6","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML 2018)","author":"Haarnoja"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref8","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"International Conference on Machine Learning","author":"Fazel"},{"key":"ref9","article-title":"LQR through the lens of first order methods: Discrete-time case","author":"Bu","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029985"},{"key":"ref11","first-page":"2916","article-title":"Derivative-free methods for policy optimization: Guarantees for linear quadratic systems","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics","author":"Malik"},{"key":"ref12","article-title":"Provably global convergence of actor-critic: A case for linear quadratic regulator with ergodic cost","volume":"32","author":"Yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3734179"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483417"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2022.3176439"},{"key":"ref16","first-page":"179","article-title":"Policy optimization for H2 linear control with H\u221e robustness guarantee: Implicit regularization and global convergence","volume-title":"Learning for Dynamics and Control","author":"Zhang","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2021.0014"},{"key":"ref18","first-page":"702","article-title":"Primal-dual learning for the model-free risk-constrained linear quadratic regulator","volume-title":"Learning for Dynamics and Control","author":"Zhao","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/ACC53348.2022.9867384"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/20M1329858"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1137\/19M123765X"},{"key":"ref22","article-title":"On topological and metrical properties of stabilizing feedback gains: the mimo case","author":"Bu","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012994272630"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(96)00141-0"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683369"},{"key":"ref27","first-page":"599","article-title":"Analysis of the optimization landscape of linear quadratic gaussian (LQG) control","volume-title":"Learning for Dynamics and Control","author":"Tang","year":"2021"},{"key":"ref28","article-title":"Analysis of the optimization landscape of linear quadratic gaussian (LQG) control","author":"Zheng","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2884649"},{"key":"ref30","volume-title":"Dynamic programming and optimal control","volume":"I","author":"Bertsekas","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2966717"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2477810"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.05.027"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2886735"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109272"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0967-0661(96)83721-x"}],"event":{"name":"2022 IEEE 61st Conference on Decision and Control (CDC)","location":"Cancun, Mexico","start":{"date-parts":[[2022,12,6]]},"end":{"date-parts":[[2022,12,9]]}},"container-title":["2022 IEEE 61st Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9992315\/9992317\/09992503.pdf?arnumber=9992503","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T17:37:13Z","timestamp":1751996233000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9992503\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/cdc51059.2022.9992503","relation":{},"subject":[],"published":{"date-parts":[[2022,12,6]]}}}