{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:41:40Z","timestamp":1775144500804,"version":"3.50.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1563454"],"award-info":[{"award-number":["1563454"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1563921"],"award-info":[{"award-number":["1563921"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1808752"],"award-info":[{"award-number":["1808752"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1808898"],"award-info":[{"award-number":["1808898"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/tnnls.2021.3071727","type":"journal-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T19:34:33Z","timestamp":1620329673000},"page":"5873-5887","source":"Crossref","is-referenced-by-count":44,"title":["Reinforcement Learning Control of Robotic Knee With Human-in-the-Loop by Flexible Policy Iteration"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3253-8000","authenticated-orcid":false,"given":"Xiang","family":"Gao","sequence":"first","affiliation":[{"name":"Department of Electrical, Computer, and Energy Engineering, Arizona State University, Tempe, AZ, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0374-7404","authenticated-orcid":false,"given":"Jennie","family":"Si","sequence":"additional","affiliation":[{"name":"Department of Electrical, Computer, and Energy Engineering, Arizona State University, Tempe, AZ, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5297-6230","authenticated-orcid":false,"given":"Yue","family":"Wen","sequence":"additional","affiliation":[{"name":"Joint Department of Biomedical Engineering, North Carolina State University, Raleigh, NC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5234-0248","authenticated-orcid":false,"given":"Minhan","family":"Li","sequence":"additional","affiliation":[{"name":"Joint Department of Biomedical Engineering, North Carolina State University, Raleigh, NC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5581-1423","authenticated-orcid":false,"given":"He","family":"Huang","sequence":"additional","affiliation":[{"name":"Joint Department of Biomedical Engineering, North Carolina State University, Raleigh, NC, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2009.2032688"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914545673"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0099387"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2014.2361937"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-015-1464-7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2012.2207895"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2014.2307256"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2017.2656130"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2019.2928514"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.007"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1126\/science.aal5054"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aar5438"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1115\/1.3140701"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1098\/rspb.2003.2454"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0081841"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-013-9979-3"},{"issue":"1","key":"ref17","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2014.109"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/9780470544785"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/9781118453988"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.923157"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.03.089"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2431734"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.2514\/2.4870"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2003.813839"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2016.7591867"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2584559"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2890974"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/72.914523"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.4.6.1107"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.005"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2761718"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2414811"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.08.023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2018.2856198"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926614"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.03.022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2281663"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-015-5462-z"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2586082"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2702566"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"ref47","first-page":"1","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Schaul"},{"key":"ref48","first-page":"1","article-title":"Distributed prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Horgan"},{"key":"ref49","first-page":"1","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Andrychowicz"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2106494"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2821369"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1002\/acs.2297"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.09.043"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2487972"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2488680"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2898370"},{"key":"ref57","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":"ref58","first-page":"20","article-title":"Policy and value transfer in lifelong reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Abel"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_5"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/1082473.1082482"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/1160633.1160762"},{"key":"ref62","first-page":"2625","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Griffith"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143906"},{"key":"ref64","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ng"},{"key":"ref65","first-page":"59","article-title":"Directed exploration in reinforcement learning with transferred knowledge","volume":"24","author":"Mann","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2017.8122863"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1682\/JRRD.2008.09.0131"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-14834-7"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2417510"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5235-x"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/9911935\/9424995-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9911935\/09424995.pdf?arnumber=9424995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:22:42Z","timestamp":1704846162000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9424995\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":70,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3071727","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}