{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T21:32:48Z","timestamp":1779399168474,"version":"3.53.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-21-1-2165"],"award-info":[{"award-number":["N00014-21-1-2165"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1109\/tii.2022.3195701","type":"journal-article","created":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T21:57:14Z","timestamp":1659477434000},"page":"6349-6363","source":"Crossref","is-referenced-by-count":16,"title":["Optimal Charging Control of Energy Storage Systems for Pulse Power Load Using Deep Reinforcement Learning in Shipboard Integrated Power Systems"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6427-3946","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"first","affiliation":[{"name":"Smart Microgrid and Renewable Technology Research Laboratory, Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2456-5618","authenticated-orcid":false,"given":"Zhenghong","family":"Tu","sequence":"additional","affiliation":[{"name":"Smart Microgrid and Renewable Technology Research Laboratory, Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7456-7606","authenticated-orcid":false,"given":"Wenxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Smart Microgrid and Renewable Technology Research Laboratory, Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2916054"},{"key":"ref15","author":"howard","year":"1960","journal-title":"Dynamic Programming and Markov Processes"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref31","first-page":"1856","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume":"3","author":"finn","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref30","article-title":"Understanding the role of the discount factor in reinforcement learning","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1049\/iet-gtd.2015.1400"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2017.2774273"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3418526"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2010.5675297"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MELE.2015.2414291"},{"key":"ref17","first-page":"148","article-title":"Reinforcement learning is direct adaptive optimal control","volume":"12","author":"sutton","year":"1992","journal-title":"IEEE Control Syst Mag"},{"key":"ref16","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.35833\/MPCE.2020.000267"},{"key":"ref23","first-page":"2587","article-title":"Addressing function approximation error in actor-critic methods","volume":"4","author":"fujimoto","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2948387"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1017\/9781108955652.016"},{"key":"ref20","first-page":"605","article-title":"Deterministic policy gradient algorithms","volume":"1","author":"silver","year":"0","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref22","first-page":"2976","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume":"5","author":"haarnoja","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref21","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent"},{"key":"ref28","article-title":"A deeper look at experience replay","author":"zhang","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109421"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.2999890"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ESTS.2005.1524672"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2014.2340393"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2010.2080329"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MIAS.2012.2215643"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MELE.2015.2413435"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMAG.2006.887676"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MELE.2015.2413434"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9424\/10116046\/09847398.pdf?arnumber=9847398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T18:34:40Z","timestamp":1686594880000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9847398\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":32,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tii.2022.3195701","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5]]}}}