{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:33:34Z","timestamp":1785857614632,"version":"3.56.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"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":["61973007"],"award-info":[{"award-number":["61973007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Southern Marine Science and Engineering Guangdong Laboratory","award":["K19313901"],"award-info":[{"award-number":["K19313901"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/tro.2022.3181014","type":"journal-article","created":{"date-parts":[[2022,6,21]],"date-time":"2022-06-21T19:44:21Z","timestamp":1655840661000},"page":"3861-3878","source":"Crossref","is-referenced-by-count":51,"title":["From Simulation to Reality: A Learning Framework for Fish-Like Robots to Perform Control Tasks"],"prefix":"10.1109","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5939-3932","authenticated-orcid":false,"given":"Tianhao","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Turbulence and Complex Systems, Intelligent Biomimetic Design Lab, College of Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runyu","family":"Tian","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Turbulence and Complex Systems, Intelligent Biomimetic Design Lab, College of Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongqi","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Turbulence and Complex Systems, Intelligent Biomimetic Design Lab, College of Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4484-8885","authenticated-orcid":false,"given":"Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Software Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinan","family":"Sun","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Software Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shikun","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Software Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6504-0087","authenticated-orcid":false,"given":"Guangming","family":"Xie","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Turbulence and Complex Systems, Intelligent Biomimetic Design Lab, College of Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Dealing with sparse rewards in reinforcement learning","author":"hare","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2017.2705059"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.compstruc.2007.01.013"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.compfluid.2007.01.007"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.compfluid.2013.09.001"},{"key":"ref30","first-page":"596","article-title":"Study on CFD-based numerical virtual flight technology and preliminary application","volume":"47","author":"chang","year":"2015","journal-title":"Chinese Journal of Theoretical Applied Mechanics"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004228"},{"key":"ref36","first-page":"2775","article-title":"Bridging the gap between value and policy based reinforcement learning","author":"nachum","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref40","first-page":"1","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"narvekar","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3084374"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49720-2_6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1115\/DSCC2018-8977"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2963246"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3054402"},{"key":"ref17","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"Proc Int Conf Learn Representations(ICLR)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2306"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2390592"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.compfluid.2015.07.023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2015.2425359"},{"key":"ref27","first-page":"267","article-title":"Validation of HyperFLOW in subsonic and transonic flow","volume":"34","author":"he","year":"2016","journal-title":"Acta Aerodynamica Sinica"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.1138353"},{"key":"ref6","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.compfluid.2003.10.004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aar3449"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2922493"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/robotics2030122"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2514\/3.13396"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3064882"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1088\/1748-3190\/11\/3\/031001"},{"key":"ref20","article-title":"Deep reinforcement learning","author":"li","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2012.2226049"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1088\/1748-3190\/ab6b6c"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2008.4739352"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.03.014"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3098239"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1088\/1748-3190\/ab6dbb"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2013.2287568"},{"key":"ref26","first-page":"4237","article-title":"CPG-based locomotion control of a robotic fish: Using linear oscillators and reducing control parameters via PSO","volume":"7","author":"wang","year":"2011","journal-title":"Int J Innov Comput Inf Control"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2651119"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1126\/science.7423199"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8860\/9970416\/09802680.pdf?arnumber=9802680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:33:24Z","timestamp":1672083204000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9802680\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":44,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tro.2022.3181014","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}