{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:48:45Z","timestamp":1775666925230,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"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":["62033006"],"award-info":[{"award-number":["62033006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1109\/tai.2021.3097313","type":"journal-article","created":{"date-parts":[[2021,8,24]],"date-time":"2021-08-24T15:18:08Z","timestamp":1629818288000},"page":"341-351","source":"Crossref","is-referenced-by-count":30,"title":["Suspension Regulation of Medium-Low-Speed Maglev Trains Via Deep Reinforcement Learning"],"prefix":"10.1109","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3142-2903","authenticated-orcid":false,"given":"Feiran","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4355-5340","authenticated-orcid":false,"given":"Keyou","family":"You","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0858-1770","authenticated-orcid":false,"given":"Shiji","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}]},{"given":"Wenyue","family":"Zhang","sequence":"additional","affiliation":[{"name":"CRRC Zhuzhou Locomotive Co. Ltd., Zhuzhou, China"}]},{"given":"Laisheng","family":"Tong","sequence":"additional","affiliation":[{"name":"CRRC Zhuzhou Locomotive Co. Ltd., Zhuzhou, China"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022628806385"},{"key":"ref30","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1080\/00207177208932211"},{"key":"ref34","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24846\/v21i1y201208"},{"key":"ref11","first-page":"295","article-title":"Modeling and control design of magnetic levitation system","author":"\u00e5uster","year":"2012","journal-title":"Proc 10th Int Symp Appl Mach Intell Informat"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2010.2057511"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2006.886248"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2011.2134530"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.09.101"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2016.03.075"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2013.10.016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA.2019.8900006"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2884725"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2015.2479404"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SII.2016.7843966"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2019.2928978"},{"key":"ref27","author":"sutton","year":"2011","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2577037"},{"key":"ref29","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2020.3017435"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2016.03.151"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2017.2771340"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/60.790940"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMAG.2006.875842"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.proeng.2013.09.097"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2879572"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2021.3075501"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2785794"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2962103"},{"key":"ref26","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proc Int Conf Mach Learn PMLR"},{"key":"ref25","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/9570826\/09484843.pdf?arnumber=9484843","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:58Z","timestamp":1755911398000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9484843\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":35,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tai.2021.3097313","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8]]}}}