{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T20:48:21Z","timestamp":1769201301481,"version":"3.49.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"ARO"},{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF"},{"name":"UC Noyce Initiative"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tac.2024.3415459","type":"journal-article","created":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T18:33:42Z","timestamp":1718649222000},"page":"8587-8602","source":"Crossref","is-referenced-by-count":2,"title":["The Landscape of Deterministic and Stochastic Optimal Control Problems: One-Shot Optimization Versus Dynamic Programming"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9692-0030","authenticated-orcid":false,"given":"Jihun","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Industrial Engineering and Operations Research, University of California, Berkeley, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1521-7566","authenticated-orcid":false,"given":"Yuhao","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering and Operations Research, University of California, Berkeley, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3229-6443","authenticated-orcid":false,"given":"Yingjie","family":"Bi","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering and Operations Research, University of California, Berkeley, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4294-1338","authenticated-orcid":false,"given":"Javad","family":"Lavaei","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering and Operations Research, University of California, Berkeley, CA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483238"},{"key":"ref2","volume-title":"Dynamic Programming","author":"Bellman","year":"1957"},{"key":"ref3","volume-title":"Dynamic Programming and Optimal Control, Two Volume Set","author":"Bertsekas","year":"2012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1957.1057416"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1287\/educ.2016.0145"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2002.1023221"},{"key":"ref7","volume-title":"Reinforcement Learning and Optimal Control","author":"Bertsekas","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2854560"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2021.12.009"},{"key":"ref12","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Allen-Zhu","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1137\/19M1299074"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1214\/17-AOS1637"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1214\/22-AOS2246"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01590-2"},{"key":"ref17","article-title":"Sharp global guarantees for nonconvex low-rank matrix recovery in the overparameterized regime","author":"Zhang","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-024-02160-6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20734"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-019-01363-6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3135361"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3137147"},{"issue":"98","key":"ref23","first-page":"1","article-title":"On the theory of policy gradient methods: Optimality, approximation, and distribution shift","volume":"22","author":"Agarwal","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref24","first-page":"2386","article-title":"On the linear convergence of policy gradient methods for finite MDPs","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Bhandari"},{"key":"ref25","first-page":"1","article-title":"On the convergence rates of policy gradient methods","volume":"23","author":"Xiao","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-022-01816-5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1137\/21M1456789"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2021.0014"},{"key":"ref29","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver","year":"2014"},{"key":"ref30","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":"ref31","first-page":"319","article-title":"Factorization approach for low-complexity matrix completion problems: Exponential number of spurious solutions and failure of gradient methods","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Yalin"},{"key":"ref32","volume-title":"Wets, Variational Analysis","volume":"317","author":"Rockafellar","year":"2009"},{"key":"ref33","volume-title":"Topological Spaces: Including a Treatment of Multi-Valued Functions, Vector Spaces, and Convexity","author":"Berge","year":"1997"},{"key":"ref34","volume-title":"Introduction to the Mathematical Theory of Control","author":"Bressan","year":"2007"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974263"},{"key":"ref36","volume-title":"Orthogonal Functions, Rev","author":"Sansone","year":"1991"},{"key":"ref37","volume-title":"Learning With Kernels","author":"Schlkopf","year":"1967"},{"key":"ref38","volume-title":"Linear Algebra and Its Applications","author":"Strang","year":"1988"},{"key":"ref39","volume-title":"Stochastic Optimal Control: The Discrete-Time Case","author":"Bertsekas","year":"1996"},{"key":"ref40","article-title":"Xpress optimizer reference manual","year":"2024"},{"key":"ref41","article-title":"Gurobi Optimizer Reference Manual","year":"2023"},{"key":"ref42","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fazel","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/20M1382386"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/9\/10778053\/10559440-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9\/10778053\/10559440.pdf?arnumber=10559440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T18:56:35Z","timestamp":1733511395000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10559440\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":43,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tac.2024.3415459","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":[[2024,12]]}}}