{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T07:09:02Z","timestamp":1773385742030,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018AAA0101501"],"award-info":[{"award-number":["2018AAA0101501"]}]},{"DOI":"10.13039\/501100010880","name":"State Grid Corporation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010880","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tii.2023.3331113","type":"journal-article","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:32:05Z","timestamp":1700598725000},"page":"5087-5099","source":"Crossref","is-referenced-by-count":8,"title":["Human\u2013Machine Collaborative Reinforcement Learning for Power Line Flow Regulation"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8406-333X","authenticated-orcid":false,"given":"Chenxi","family":"Wang","sequence":"first","affiliation":[{"name":"Ministry of Education Key Lab for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1714-3433","authenticated-orcid":false,"given":"Youtian","family":"Du","sequence":"additional","affiliation":[{"name":"Ministry of Education Key Lab for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6764-5150","authenticated-orcid":false,"given":"Yuanlin","family":"Chang","sequence":"additional","affiliation":[{"name":"Ministry of Education Key Lab for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihao","family":"Guo","sequence":"additional","affiliation":[{"name":"Ministry of Education Key Lab for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanhao","family":"Huang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Power Grid Safety and Energy Conservation, China Electric Power Research Institute, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.17775\/CSEEJPES.2019.00920"},{"key":"ref2","article-title":"Introducing machine learning for power system operation support","volume-title":"IREP Symp.","author":"Donnot","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref5","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2008.919414"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/PESGM41954.2020.9281849"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3084139"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2933191"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06008-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/APPEEC.2016.7779788"},{"key":"ref13","first-page":"291","article-title":"A reinforcement learning framework for optimal operation and maintenance of power grids","volume-title":"Appl. Energy","volume":"241","author":"Rocchetta","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3035406"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2956509"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/212"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2020.07.011"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298824"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2017.2738618"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/PESW.2000.849925"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2019.2941134"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/PESGM40551.2019.8973924"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1186\/s13677-021-00259-1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.bushor.2018.03.007"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114837"},{"key":"ref27","article-title":"Towards an AI assistant for human grid operators","volume-title":"Hybrid Human-Artif. Intell.","author":"Marot","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CAC51589.2020.9327043"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3105115"},{"key":"ref30","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref32","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref33","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2829021"},{"key":"ref35","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref36","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9424\/10492489\/10324406.pdf?arnumber=10324406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T20:01:41Z","timestamp":1712692901000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10324406\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":36,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tii.2023.3331113","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}