{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:21:26Z","timestamp":1740100886168,"version":"3.37.3"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"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":[[2022,6,8]]},"DOI":"10.23919\/acc53348.2022.9867384","type":"proceedings-article","created":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T20:24:10Z","timestamp":1662409450000},"page":"2932-2937","source":"Crossref","is-referenced-by-count":6,"title":["Optimization Landscape of Gradient Descent for Discrete-time Static Output Feedback"],"prefix":"10.23919","author":[{"given":"Jingliang","family":"Duan","sequence":"first","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,School of Vehicle and Mobility,Beijing,China,100084"}]},{"given":"Shengbo Eben","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,School of Vehicle and Mobility,Beijing,China,100084"}]},{"given":"Lin","family":"Zhao","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718768"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/17M1114296"},{"key":"ref30","first-page":"797","article-title":"Escaping from saddle points—online stochastic gradient for tensor decomposition","author":"ge","year":"2015","journal-title":"Conference on Learning Theory"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2884649"},{"article-title":"LQR through the lens of first order methods: Discrete-time case","year":"2019","author":"bu","key":"ref10"},{"key":"ref11","article-title":"Global optimality guarantees for policy gradient methods","author":"bhandari","year":"2019","journal-title":"arXiv preprint arXiv 1906 04329"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029985"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1137\/20M1329858"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/20M1382386"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483417"},{"article-title":"Policy optimization for markovian jump linear quadratic control: Gradient-based methods and global convergence","year":"2020","author":"jansch-porto","key":"ref16"},{"key":"ref17","first-page":"287","article-title":"Learning the globally optimal distributed LQ regulator","author":"furieri","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"ref18","first-page":"179","article-title":"Policy optimization for H2 linear control with H? robustness guarantee: Implicit regularization and global convergence","author":"zhang","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"ref19","first-page":"599","article-title":"Analysis of the optimization landscape of linear quadratic gaussian (LQG) control","author":"tang","year":"2021","journal-title":"Learning for Dynamics and Control"},{"key":"ref28","first-page":"2","article-title":"A topological property of real analytic subsets","volume":"117","author":"lojasiewicz","year":"1963","journal-title":"Coll du CNRS Lés equations aux dérivées partielles"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref27","first-page":"5","article-title":"Introductory lectures on convex programming volume i: Basic course","volume":"3","author":"nesterov","year":"1998","journal-title":"Lecture notes"},{"key":"ref3","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"4th International Conference on Learning Representations (ICLR 2016)"},{"key":"ref6","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML 2015)"},{"key":"ref29","first-page":"1724","article-title":"How to escape saddle points efficiently","author":"jin","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2019.0317"},{"key":"ref8","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning (ICML 2018)"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref9","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","author":"fazel","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref20","first-page":"559","article-title":"Sample complexity of linear quadratic gaussian (LQG) control for output feedback systems","author":"zheng","year":"2021","journal-title":"Learning for Dynamics and Control"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/19M123765X"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(96)00141-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1134\/S0005117908120011"},{"article-title":"On topological and metrical properties of stabilizing feedback gains: the mimo case","year":"2019","author":"bu","key":"ref23"},{"key":"ref26","first-page":"643","article-title":"Gradient methods for minimizing functionals","volume":"3","author":"polyak","year":"1963","journal-title":"Zhurnal Vychislitel’noi Matematiki i Matematicheskoi Fiziki"},{"article-title":"Optimization landscape of gradient descent for discrete-time static output feedback","year":"2021","author":"duan","key":"ref25"}],"event":{"name":"2022 American Control Conference (ACC)","start":{"date-parts":[[2022,6,8]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2022,6,10]]}},"container-title":["2022 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9866948\/9867142\/09867384.pdf?arnumber=9867384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T20:38:20Z","timestamp":1664829500000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9867384\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,8]]},"references-count":34,"URL":"https:\/\/doi.org\/10.23919\/acc53348.2022.9867384","relation":{},"subject":[],"published":{"date-parts":[[2022,6,8]]}}}