{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:44:29Z","timestamp":1770918269353,"version":"3.50.1"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"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":["52307085"],"award-info":[{"award-number":["52307085"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Key Laboratory of Smart Grid Technology and Equipment"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Smart Grid"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tsg.2024.3382293","type":"journal-article","created":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T19:22:09Z","timestamp":1711567329000},"page":"4618-4635","source":"Crossref","is-referenced-by-count":24,"title":["Offline DRL for Price-Based Demand Response: Learning From Suboptimal Data and Beyond"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6251-4574","authenticated-orcid":false,"given":"Tao","family":"Qian","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyu","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7067-1713","authenticated-orcid":false,"given":"Chengcheng","family":"Shao","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and the State Key Laboratory on Electrical Insulation and Power Equipment, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8294-6419","authenticated-orcid":false,"given":"Hongcai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5398-5718","authenticated-orcid":false,"given":"Qinran","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1173-809X","authenticated-orcid":false,"given":"Zaijun","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tsg.2016.2547883"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tsg.2014.2376522"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tsg.2015.2413951"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tsg.2021.3128547"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tsg.2021.3121686"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2022.112095"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3135561"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2018.2826454"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2949263"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2834368"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2015.2414719"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2013.12.069"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2413813"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2012.2207134"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2015.2391774"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2017.2750706"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2703132"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2795007"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2022.120167","article-title":"An optimal bidding and scheduling method for load service entities considering demand response uncertainty","volume":"328","author":"Han","year":"2022","journal-title":"Appl. Energy"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2022.3166954"},{"key":"ref21","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2021.3111014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.2969650"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3131804"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3181329"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3109954"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3168856"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.2978061"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2022.3172068"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.17775\/CSEEJPES.2020.03120"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.2967430"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tsg.2020.3037066"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tsg.2023.3330990"},{"key":"ref34","article-title":"Offline reinforcement learning: tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tie.2021.3116581"},{"key":"ref36","article-title":"Off-policy deep reinforcement learning without exploration","author":"Fujimoto","year":"2018","journal-title":"arXiv:1812.02900"},{"key":"ref37","article-title":"Conservative Q-learning for offline reinforcement learning","author":"Kumar","year":"2020","journal-title":"arXiv:2006.04779"},{"key":"ref38","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv:1911.11361"},{"key":"ref39","article-title":"When should we prefer offline reinforcement learning over behavioral cloning?","author":"Kumar","year":"2022","journal-title":"arXiv:2204.05618"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ciss56502.2023.10089681"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TICPS.2023.3294874"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.120240"},{"key":"ref43","volume-title":"Bayesian reinforcement learning: A survey","author":"Ghavamzadeh","year":"2016"},{"key":"ref44","volume-title":"A Bayesian perspective on Q-learning","author":"Da Silva","year":"2020"},{"key":"ref45","first-page":"661","article-title":"Efficient reductions for imitation learning","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","volume":"9","author":"Ross"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3219109"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3206511"},{"key":"ref48","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018","journal-title":"arXiv:1802.09477"},{"key":"ref49","article-title":"Geometric GAN","author":"Lim","year":"2017","journal-title":"arXiv.1705.02894"},{"key":"ref50","first-page":"1","article-title":"Learning from Limited Demonstrations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref51","volume-title":"Learning complex dexterous manipulation with deep reinforcement learning and demonstrations","author":"Rajeswaran","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2019.8794102"},{"key":"ref53","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2018","journal-title":"arXiv.1707.08817"},{"key":"ref54","article-title":"Offline-to-online reinforcement learning via balanced replay and pessimistic Q-ensemble","author":"Lee","year":"2021","journal-title":"arXiv.2107.00591"}],"container-title":["IEEE Transactions on Smart Grid"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165411\/10643567\/10480734.pdf?arnumber=10480734","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T03:59:48Z","timestamp":1725249588000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10480734\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":54,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tsg.2024.3382293","relation":{},"ISSN":["1949-3053","1949-3061"],"issn-type":[{"value":"1949-3053","type":"print"},{"value":"1949-3061","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}