{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T20:21:57Z","timestamp":1777666917972,"version":"3.51.4"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2016YFB0901900"],"award-info":[{"award-number":["2016YFB0901900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673229"],"award-info":[{"award-number":["61673229"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"111 International Collaboration Project of China","award":["BP2018006"],"award-info":[{"award-number":["BP2018006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1109\/tase.2020.2995914","type":"journal-article","created":{"date-parts":[[2020,6,5]],"date-time":"2020-06-05T20:55:01Z","timestamp":1591390501000},"page":"681-692","source":"Crossref","is-referenced-by-count":17,"title":["A Computing Budget Allocation Method for Minimizing EV Charging Cost Using Uncertain Wind Power"],"prefix":"10.1109","volume":"18","author":[{"given":"Zhaoyu","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing-Shan","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohong","family":"Guan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc 13th AAAI Conf Artif Intell"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2879572"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref32","first-page":"341","article-title":"Solving Markov decision processes via simulation","author":"abhijit","year":"2015","journal-title":"Handbook of Simulation Optimization"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-642-27645-3_1","article-title":"Reinforcement learning and Markov decision processes","author":"otterlo","year":"2012","journal-title":"Reinforcement Learning"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2017.8256209"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref36","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10626-013-0170-6"},{"key":"ref34","article-title":"On-line Q-learning using connectionist systems","author":"rummery","year":"1994"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2541305"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2014.2302316"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/57.1.97"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2014.2301931"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.enconman.2015.11.015"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-018-9621-8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2013.2295591"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2016.2585180"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2014.2385711"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2018.2856908"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2574799"},{"key":"ref26","volume":"7","author":"altman","year":"1999","journal-title":"Constrained Markov Decision Processes"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2791425"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2018.8560473"},{"key":"ref59","author":"degroot","year":"1970","journal-title":"Optimal Statistical Decisions"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2011.2181191"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2010.2061243"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1999.832818"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2013.10.030"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2797188"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2016.1581"},{"key":"ref52","author":"chen","year":"2011","journal-title":"Stochastic Simulation Optimization An Optimal Computing Budget Allocation"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2017.2788440"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2017.2707103"},{"key":"ref40","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015","journal-title":"arXiv 1511 06581"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2878809"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2014.02.003"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2906186"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2567066"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-018-9597-8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2011.2174059"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2015.2391284"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2009.2036481"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2012.2214069"},{"key":"ref3","first-page":"51","article-title":"A review of multi-temporal-and-spatial-scale wind power forecasting method","volume":"45","author":"jiang","year":"2019","journal-title":"ACTA Automatica Sinica"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2011.2181164"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009634810396"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2423832"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008349927281"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2423832"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.900656"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1561\/2200000071"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1080.0268"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2012.2195931"},{"key":"ref42","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref41","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent"},{"key":"ref44","article-title":"Combining policy gradient and Q-learning","author":"o\u2019donoghue","year":"2017","journal-title":"Proc 5th Int Conf Learn Represent"},{"key":"ref43","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8856\/9397439\/09109580.pdf?arnumber=9109580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:52:29Z","timestamp":1652194349000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9109580\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4]]},"references-count":60,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tase.2020.2995914","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4]]}}}