{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:52:16Z","timestamp":1774630336483,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T00:00:00Z","timestamp":1707955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T00:00:00Z","timestamp":1707955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T00:00:00Z","timestamp":1707955200000},"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":["61772001"],"award-info":[{"award-number":["61772001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2024,2,15]]},"DOI":"10.1109\/jiot.2023.3314522","type":"journal-article","created":{"date-parts":[[2023,9,12]],"date-time":"2023-09-12T17:36:16Z","timestamp":1694540176000},"page":"6582-6595","source":"Crossref","is-referenced-by-count":4,"title":["Toward Fair Power Grid Control: A Hierarchical Multiobjective Reinforcement Learning Approach"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5353-0844","authenticated-orcid":false,"given":"Xiang","family":"Hu","sequence":"first","affiliation":[{"name":"School of Control and Computer Engineering, North China Electric Power University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9996-0070","authenticated-orcid":false,"given":"Yuhui","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Control and Computer Engineering, North China Electric Power University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1172-9545","authenticated-orcid":false,"given":"Hongke","family":"Xia","sequence":"additional","affiliation":[{"name":"Computer School, Beijing Information Science and Technology University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9810-4496","authenticated-orcid":false,"given":"Wenjiang","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Control and Computer Engineering, North China Electric Power University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7904-9269","authenticated-orcid":false,"given":"Qihui","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Control and Computer Engineering, North China Electric Power University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9800-5923","authenticated-orcid":false,"given":"Jianlong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Control and Computer Engineering, North China Electric Power University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3042007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3160864"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3021429"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2013.2255135"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2013.2294187"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2014.2321762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/PESGM41954.2020.9281518"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3046622"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2019.2941134"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2933191"},{"key":"ref11","article-title":"LEAP nets for power grid perturbations","author":"Donnot","year":"2019","journal-title":"arXiv:1908.08314"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.12.135"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3040294"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3062700"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2022.3171534"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2020.106635"},{"key":"ref17","first-page":"1","article-title":"Winning the L2RPN challenge: Power grid management via semi-Markov afterstate actor-critic","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yoon"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86517-7_11"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2022.108487"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9216899"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/info10100315"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.3027695"},{"key":"ref23","first-page":"8905","article-title":"Learning fair policies in multiobjective deep reinforcement learning with average and discounted rewards","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Siddique"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0165-4896(81)90018-4"},{"key":"ref25","article-title":"Reinforcement learning for electricity network operation","author":"Kelly","year":"2020","journal-title":"arXiv:2003.07339"},{"key":"ref26","first-page":"1","article-title":"L2RPN: Learning to run a power network in a sustainable world NeurIPS 2020 challenge design","volume-title":"Proc. NeurIPS","author":"Marot"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2017.2745410"},{"issue":"1","key":"ref28","first-page":"3483","article-title":"multiobjective reinforcement learning using sets of Pareto dominating policies","volume":"15","author":"Van Moffaert","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3987"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/9780470172261"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2014.2358639"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/311"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532035"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2307\/1959089"},{"key":"ref35","first-page":"1","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Sutton"},{"key":"ref36","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref37","first-page":"112","article-title":"Learning to run a power network challenge: A retrospective analysis","volume-title":"Proc. NeurIPS Competition Demonstration Track","author":"Marot"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/10419857\/10247509.pdf?arnumber=10247509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,14]],"date-time":"2024-02-14T15:03:16Z","timestamp":1707922996000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10247509\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,15]]},"references-count":38,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2023.3314522","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,15]]}}}