{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T01:11:00Z","timestamp":1781313060259,"version":"3.54.1"},"reference-count":31,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"2","funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS-2205972"],"award-info":[{"award-number":["DMS-2205972"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Control Optim."],"published-print":{"date-parts":[[2026,4,30]]},"DOI":"10.1137\/24m1680039","type":"journal-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T07:36:31Z","timestamp":1775720191000},"page":"816-842","source":"Crossref","is-referenced-by-count":1,"title":["Convergence Analysis for Entropy-Regularized Control Problems: A Probabilistic Approach"],"prefix":"10.1137","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6780-0956","authenticated-orcid":true,"given":"Jin","family":"Ma","sequence":"first","affiliation":[{"name":"Department of Mathematics, University of Southern California, Los Angeles, CA 90089-2532 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8795-8366","authenticated-orcid":true,"given":"Gaozhan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of Southern California, Los Angeles, CA 90089-2532 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of Southern California, Los Angeles, CA 90089-2532 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2026,4,9]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","unstructured":"L. Bai, T. Gamage, J. Ma, and G. Wang, Reinforcement Learning for Optimal Dividend Problem Under Diffusion Model, preprint, http:\/\/dx.doi.org\/10.2139\/ssrn.6365859, 2026.","DOI":"10.2139\/ssrn.5313612"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.41.10.743"},{"key":"ref3","volume-title":"Dynamic Programming","author":"Bellman R.","year":"1957"},{"key":"ref4","series-title":"Progr. Math. 45","volume-title":"Large Deviation and Malliavin Calculus","author":"Bismut J. M.","year":"1984"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/08073041X"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1137\/22M1516725"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1006\/jfan.1994.1124"},{"key":"ref8","series-title":"Probab. Math. Statist. 28","volume-title":"Stochastic Differential Equations and Applications, Vol.\u00a01","author":"Friedman A.","year":"1975"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2021.1238"},{"key":"ref10","volume-title":"Dynamic Programming and Markov Processes","author":"Howard R. A.","year":"1960"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1137\/24M1638744"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-020-09460-1"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/17442508.2016.1187609"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/19M1236758"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s00245-021-09750-2"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/012"},{"key":"ref17","unstructured":"J. Ma, G. Wang, J. Zhang, and X. Y. Zhou, Reinforcement Learning Algorithms for Entropy-Regularized HJB Equations with Model Uncertainty, working paper."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1214\/aoap\/1037125868"},{"key":"ref19","volume-title":"The Malliavin Calculus and Related Topics","author":"Nualart D.","year":"2006","edition":"2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF00935182"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1287\/moor.4.1.60"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/22M1492180"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/20M1312435"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012902399824"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/24M166591X"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/21M1448185"},{"key":"ref27","unstructured":"W. Tang and X. Y. Zhou, Regret of Exploratory Policy Improvement and \\(q\\)-Learning, preprint, arXiv:2411.01302, 2024."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s00245-025-10249-3"},{"key":"ref29","first-page":"1","volume":"21","author":"Wang H.","year":"2020","journal-title":"J. Mach. Learn. Res"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1111\/mafi.12281"},{"key":"ref31","unstructured":"J. Zhang, Some Fine Properties of Backward Stochastic Differential Equations, Ph.D. dissertation, Purdue University, 2001."}],"container-title":["SIAM Journal on Control and Optimization"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T07:36:37Z","timestamp":1775720197000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/24M1680039"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,9]]},"references-count":31,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1137\/24M1680039"],"URL":"https:\/\/doi.org\/10.1137\/24m1680039","relation":{},"ISSN":["0363-0129","1095-7138"],"issn-type":[{"value":"0363-0129","type":"print"},{"value":"1095-7138","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,9]]}}}