{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:40:03Z","timestamp":1783701603917,"version":"3.55.0"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"PolyU for RISE Seed Project","award":["U-CDC8"],"award-info":[{"award-number":["U-CDC8"]}]},{"name":"PolyU for PReCIT Seed Project","award":["1-CE16"],"award-info":[{"award-number":["1-CE16"]}]},{"name":"PolyU for Intra-Faculty Interdisciplinary Project","award":["1-WZ4L"],"award-info":[{"award-number":["1-WZ4L"]}]},{"name":"Beijing Normal-Hong Kong Baptist University for Start-up Fund","award":["UICR0700116-25"],"award-info":[{"award-number":["UICR0700116-25"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tnnls.2025.3574208","type":"journal-article","created":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T13:45:24Z","timestamp":1749649524000},"page":"19270-19284","source":"Crossref","is-referenced-by-count":7,"title":["Deep Reinforcement Learning Approach for Dynamic Distribution Network Reconfiguration Based on Sequential Masking"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8865-1785","authenticated-orcid":false,"given":"Ruoheng","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6513-6521","authenticated-orcid":false,"given":"Xiaowen","family":"Bi","sequence":"additional","affiliation":[{"name":"Department of Statistics and Data Science, Guangdong Provincial\/Zhuhai Key Laboratory of IRADS, Beijing Normal-Hong Kong Baptist University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1047-2568","authenticated-orcid":false,"given":"Siqi","family":"Bu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Shenzhen Research Institute, the Research Center for Grid Modernisation, the Research Institute for Smart Energy, the Policy Research Center for Innovation and Technology, the International Center of Urban Energy Nexus, and the Center for Advances in Reliability and Safety, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhixian","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2019.01.010"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3103934"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3005270"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRD.2021.3107534"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3097330"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2016.08.011"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2017.2738014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2011.2180406"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2017.02.010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2012.2197227"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2023.3324474"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.115900"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3089625"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2963696"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2015.2457954"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2021.3102870"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.aej.2021.12.012"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2024.3371093"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3243549"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s00202-021-01399-y"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.rineng.2024.102026"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1088\/1755-1315\/571\/1\/012023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1049\/gtd2.12433"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2829021"},{"key":"ref25","first-page":"3271","article-title":"Multi-agent reinforcement learning for active voltage control on power distribution networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Wang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/363219.363232"},{"key":"ref27","first-page":"2692","article-title":"Pointer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Vinyals"},{"key":"ref28","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref29","first-page":"1","article-title":"Categorical reparameterization with Gumbel-Softmax","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jang"},{"key":"ref30","article-title":"Soft actor-critic for discrete action settings","author":"Christodoulou","year":"2019","journal-title":"arXiv:1910.07207"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2946414"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.118189"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2017.2669343"},{"key":"ref35","first-page":"9861","article-title":"Reinforcement learning for solving the vehicle routing problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Nazari"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11195929\/11030288.pdf?arnumber=11030288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:38:33Z","timestamp":1759945113000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11030288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":35,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3574208","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}