{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T19:14:08Z","timestamp":1775848448834,"version":"3.50.1"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003621","name":"Korea Government","doi-asserted-by":"publisher","award":["2021R1C1C1008474"],"award-info":[{"award-number":["2021R1C1C1008474"]}],"id":[{"id":"10.13039\/501100003621","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Control Syst. Lett."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/lcsys.2021.3086672","type":"journal-article","created":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T20:32:54Z","timestamp":1622838774000},"page":"1094-1099","source":"Crossref","is-referenced-by-count":6,"title":["Learning Stochastic Optimal Policies via Gradient Descent"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3788-6290","authenticated-orcid":false,"given":"Stefano","family":"Massaroli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5384-9372","authenticated-orcid":false,"given":"Michael","family":"Poli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefano","family":"Peluchetti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2620-1479","authenticated-orcid":false,"given":"Jinkyoo","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1280-069X","authenticated-orcid":false,"given":"Atsushi","family":"Yamashita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9482-497X","authenticated-orcid":false,"given":"Hajime","family":"Asama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1093\/rfs\/15.3.805"},{"key":"ref31","volume":"3","author":"khalil","year":"2002","journal-title":"Nonlinear Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmaa.2004.06.051"},{"key":"ref37","article-title":"Smoking adjoints: Fast evaluation of greeks in Monte Carlo calculations","author":"giles","year":"2005"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012902419059"},{"key":"ref35","author":"nocedal","year":"2006","journal-title":"Numerical Optimization"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/1119062"},{"key":"ref10","first-page":"1126","article-title":"Infinitely deep neural networks as diffusion processes","author":"peluchetti","year":"2020","journal-title":"Proc Int Conf Artif Intell Stat"},{"key":"ref11","author":"arnold","year":"1974","journal-title":"Stochastic Differential Equations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-0007-6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref14","volume":"1","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref15","first-page":"287","article-title":"Learning the globally optimal distributed LQ regulator","author":"furieri","year":"2020","journal-title":"Proc Learn Dyn Control"},{"key":"ref16","author":"bu","year":"2019","journal-title":"LQR through the lens of first order methods Discrete-time case"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BF01007642"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14394-6_5"},{"key":"ref19","first-page":"1352","article-title":"Differential equations determining a markoff process","volume":"1077","author":"it\u00f4","year":"1942","journal-title":"J Pan-Japanese Math Colloq"},{"key":"ref28","first-page":"2332","article-title":"Global convergence of stochastic gradient descent for some non-convex matrix problems","author":"de sa","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","author":"levine","year":"2018","journal-title":"Reinforcement Learning and Control as Probabilistic Inference Tutorial and Review"},{"key":"ref27","author":"ruder","year":"2016","journal-title":"An overview of gradient descent optimization algorithms"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2661863"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012996313549"},{"key":"ref29","first-page":"699","article-title":"Variance reduction for faster non-convex optimization","author":"allen-zhu","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1972.1099867"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9028871"},{"key":"ref7","first-page":"70","article-title":"Learning deep stochastic optimal control policies using forward-backward SDEs","author":"pereira","year":"2019","journal-title":"Proc Robot Sci Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-012-1128-z"},{"key":"ref9","author":"massaroli","year":"2020","journal-title":"Dissecting Neural ODEs"},{"key":"ref1","author":"bertsekas","year":"1996","journal-title":"Stochastic Optimal Control The Discrete-Time Case"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/0304028"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177699916"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-3801-4"},{"key":"ref24","volume":"24","author":"kunita","year":"1997","journal-title":"Stochastic Flows and Stochastic Differential Equations"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2307\/1926560"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref25","author":"li","year":"2020","journal-title":"Scalable gradients for stochastic differential equations"}],"container-title":["IEEE Control Systems Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782633\/9462165\/09446979.pdf?arnumber=9446979","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,8]],"date-time":"2021-11-08T22:21:39Z","timestamp":1636410099000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9446979\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/lcsys.2021.3086672","relation":{},"ISSN":["2475-1456"],"issn-type":[{"value":"2475-1456","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}