{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T03:22:01Z","timestamp":1775186521514,"version":"3.50.1"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"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":["62422308"],"award-info":[{"award-number":["62422308"]}],"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":["62233006"],"award-info":[{"award-number":["62233006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Foundation for Outstanding Research Groups of Hubei Province of China","award":["2025AFA012"],"award-info":[{"award-number":["2025AFA012"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tnnls.2024.3496932","type":"journal-article","created":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T19:17:30Z","timestamp":1734031050000},"page":"9985-9999","source":"Crossref","is-referenced-by-count":13,"title":["Lyapunov-Based Safe Reinforcement Learning for Microgrid Energy Management"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6409-1958","authenticated-orcid":false,"given":"Guokai","family":"Hao","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8052-1233","authenticated-orcid":false,"given":"Yuanzheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6515-4567","authenticated-orcid":false,"given":"Yang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Northeast Electric Power University, Jilin City, China"}]},{"given":"Lin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4587-3588","authenticated-orcid":false,"given":"Zhigang","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3170070"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3185211"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s44287-024-00018-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3232630"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3175418"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2022.3156069"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.2970678"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3113573"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.2976771"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3034827"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2022.3212938"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3078462"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3160387"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3088290"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tste.2024.3356259"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3149266"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3303358"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRD.2021.3107534"},{"key":"ref19","first-page":"801","article-title":"Safe policy learning for continuous control","volume-title":"Proc. Conf. Robot Learn.","volume":"155","author":"Chow"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2023.121490"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpwrs.2024.3421272"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2023.3243170"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2023.120759"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2022.3178415"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2024.3390808"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI50451.2021.9659545"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tte.2024.3362707"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2018.2858183"},{"key":"ref29","volume-title":"Gurobi Optimizer Reference Manual","year":"2023"},{"key":"ref30","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref31","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref32","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Schulman"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2016.08.060"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2021.3099336"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11022714\/10795439.pdf?arnumber=10795439","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T17:57:23Z","timestamp":1749059843000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10795439\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":34,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3496932","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}