{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T22:12:26Z","timestamp":1772489546917,"version":"3.50.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12501430"],"award-info":[{"award-number":["12501430"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72394363\/72394360"],"award-info":[{"award-number":["72394363\/72394360"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12431011"],"award-info":[{"award-number":["12431011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72394364"],"award-info":[{"award-number":["72394364"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72071139"],"award-info":[{"award-number":["72071139"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024300418"],"award-info":[{"award-number":["2024300418"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2025300110"],"award-info":[{"award-number":["2025300110"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Research Fund from MOE Key Laboratory of NSLSCS"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tac.2025.3621539","type":"journal-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T17:43:02Z","timestamp":1760463782000},"page":"2015-2022","source":"Crossref","is-referenced-by-count":0,"title":["Nonconvex Regularization for Markov Decision Processes: Modeling and Algorithms"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8717-4107","authenticated-orcid":false,"given":"Yuwei","family":"Wu","sequence":"first","affiliation":[{"name":"School of Management and Engineering, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8057-3690","authenticated-orcid":false,"given":"Caihua","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Management and Engineering, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3929-4707","authenticated-orcid":false,"given":"Chunlin","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Management and Engineering, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7109-3379","authenticated-orcid":false,"given":"Suhong","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Accounting, Nanjing University of Finance and Economics, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0510-8080","authenticated-orcid":false,"given":"Andrew","family":"Lim","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_18"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2018.09.005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref5","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref6","volume-title":"Dynamic Programming and Markov Processes","author":"Howard","year":"1960"},{"key":"ref7","volume-title":"Dynamic Programming","author":"Bellman","year":"1957"},{"key":"ref8","first-page":"1125","article-title":"SBEED: Convergent reinforcement learning with nonlinear function approximation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dai","year":"2018"},{"issue":"2","key":"ref9","first-page":"161","article-title":"Les problmes de dcisions squentielles","volume":"2","author":"Ghellinck","year":"1960","journal-title":"Cahiers du Centre dEtudes de Recherche Oprationnelle"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.10.1.98"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1050.0149"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1110.0516"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2014.0699"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-85450-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/070703983"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/080725891"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1051\/m2an\/197509r200411"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/0898-1221(76)90003-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/110853996"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1137\/110822347"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2012.700713"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF01581204"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-014-0826-5"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-016-1034-2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/140990309"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1023\/A:1004603514434"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3112851"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1111\/ecog.00888"},{"key":"ref30","first-page":"761","article-title":"Bayesian Q-learning","volume-title":"Proc. 15th Nat. Conf. Artif. Intell.\/Innov. Appl. Artif. Intell. USA: Amer. Assoc. Artif. Intell.","author":"Dearden","year":"1998"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-017-9366-8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-011-0484-9"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9\/11417357\/11202659.pdf?arnumber=11202659","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T20:59:07Z","timestamp":1772485147000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11202659\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":32,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tac.2025.3621539","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":[[2026,3]]}}}