{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T19:37:44Z","timestamp":1785267464263,"version":"3.55.0"},"reference-count":30,"publisher":"Informa UK Limited","issue":"1","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62233006, 62173221"],"award-info":[{"award-number":["62233006, 62173221"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Rising-Star program","award":["20QA1404000"],"award-info":[{"award-number":["20QA1404000"]}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Journal of Control and Decision"],"published-print":{"date-parts":[[2025,1,2]]},"DOI":"10.1080\/23307706.2023.2201587","type":"journal-article","created":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T09:45:35Z","timestamp":1682415935000},"page":"101-110","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":7,"title":["Robustness enhancement of DRL controller for DC\u2013DC buck converters fusing ESO"],"prefix":"10.1080","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4244-3208","authenticated-orcid":false,"given":"Tianxiao","family":"Yang","sequence":"first","affiliation":[{"name":"Intelligent Autonomous Systems Lab, Shanghai University of Electric Power, Shanghai, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9463-384X","authenticated-orcid":false,"given":"Chengang","family":"Cui","sequence":"additional","affiliation":[{"name":"Intelligent Autonomous Systems Lab, Shanghai University of Electric Power, Shanghai, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6052-1682","authenticated-orcid":false,"given":"Chuanlin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Intelligent Autonomous Systems Lab, Shanghai University of Electric Power, Shanghai, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4290-9568","authenticated-orcid":false,"given":"Jun","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Aeronautical and Automotive Engineering, Loughborough University, Loughborough, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2023,4,25]]},"reference":[{"key":"e_1_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2854885"},{"key":"e_1_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.35833\/MPCE.2020.000552"},{"key":"e_1_3_2_4_1","unstructured":"Coggan M. (2004). Exploration and exploitation in reinforcement learning. Research supervised by Prof. Doina Precup CRA-W DMP Project at McGill University."},{"key":"e_1_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2021.3107535"},{"key":"e_1_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3192676"},{"key":"e_1_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPEL.2006.876848"},{"key":"e_1_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2767550"},{"key":"e_1_3_2_9_1","unstructured":"Fan J. Wang Z. Xie Y. & Yang Z. (2020). A theoretical analysis of deep Q-learning. In Learning for dynamics and control (pp. 486\u2013489)."},{"key":"e_1_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3005071"},{"key":"e_1_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPEL.63"},{"key":"e_1_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2008.2011621"},{"key":"e_1_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/JESTPE.2022.3189078"},{"key":"e_1_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"e_1_3_2_15_1","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar A.","year":"2020","unstructured":"Kumar, A., Zhou, A., Tucker, G., & Levine, S. (2020). Conservative q-learning for offline reinforcement learning. Advances in Neural Information Processing Systems, 33, 1179\u20131191.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPEL.2010.2091285"},{"key":"e_1_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2022.03.019"},{"key":"e_1_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPEL.2021.3089707"},{"key":"e_1_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.28"},{"key":"e_1_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3098169"},{"key":"e_1_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3054790"},{"key":"e_1_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-3099-6"},{"key":"e_1_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1080\/23307706.2018.1549516"},{"key":"e_1_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2017.2751755"},{"key":"e_1_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.25"},{"key":"e_1_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA54724.2022.9831887"},{"key":"e_1_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/820"},{"key":"e_1_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.5165411"},{"key":"e_1_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.41"},{"key":"e_1_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"e_1_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2007.4434676"}],"container-title":["Journal of Control and Decision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/23307706.2023.2201587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,12]],"date-time":"2025-01-12T06:41:07Z","timestamp":1736664067000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/23307706.2023.2201587"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,25]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1,2]]}},"alternative-id":["10.1080\/23307706.2023.2201587"],"URL":"https:\/\/doi.org\/10.1080\/23307706.2023.2201587","relation":{},"ISSN":["2330-7706","2330-7714"],"issn-type":[{"value":"2330-7706","type":"print"},{"value":"2330-7714","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,25]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tjcd20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tjcd20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2022-11-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-04-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-04-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}