{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T09:10:07Z","timestamp":1770973807082,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2016,10,1]],"date-time":"2016-10-01T00:00:00Z","timestamp":1475280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health fellowship","doi-asserted-by":"publisher","award":["TRN030167"],"award-info":[{"award-number":["TRN030167"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Veterans Administration Rehabilitation Research and Development predoctoral fellowship"},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["T32 EB004314"],"award-info":[{"award-number":["T32 EB004314"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ardiem Medical Arm Control Device","award":["W81XWH0720044"],"award-info":[{"award-number":["W81XWH0720044"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Human-Mach. Syst."],"published-print":{"date-parts":[[2016,10]]},"DOI":"10.1109\/thms.2016.2558630","type":"journal-article","created":{"date-parts":[[2016,5,24]],"date-time":"2016-05-24T14:15:08Z","timestamp":1464099308000},"page":"723-733","source":"Crossref","is-referenced-by-count":22,"title":["Human-Like Rewards to Train a Reinforcement Learning Controller for Planar Arm Movement"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2755-2097","authenticated-orcid":false,"given":"Kathleen M.","family":"Jagodnik","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip S.","family":"Thomas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonie J.","family":"van den Bogert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael S.","family":"Branicky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert F.","family":"Kirsch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1006\/exnr.1997.6690"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014237"},{"key":"ref33","volume":"414","author":"puterman","year":"2005","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref32","first-page":"345","article-title":"Reinforcement learning algorithm for partially observable Markov decision problems","volume":"7","author":"jaakkola","year":"1995","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref31","first-page":"393","article-title":"Reinforcement learning methods for continuous-time Markov decision problems","volume":"7","author":"bradtke","year":"1995","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: a survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"J Artif Intell Res"},{"key":"ref37","first-page":"792","article-title":"Principled methods for advising reinforcement learning agents","author":"wiewiora","year":"0","journal-title":"Proc 20th Int Conf Mach Learning"},{"key":"ref36","article-title":"Making reinforcement learning work on real robots","author":"smart","year":"2002"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"ref34","article-title":"Framing human-robot task communication as a partially observable Markov decision process","author":"woodward","year":"2012"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-013-1099-5"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/sj.sc.3102131"},{"key":"ref11","article-title":"Learning from feedback on actions past and intended","author":"knox","year":"0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2466\/pms.1989.69.1.243"},{"key":"ref13","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008819414322"},{"key":"ref15","article-title":"A reinforcement learning controller for functional electrical stimulation of a human arm","author":"thomas","year":"2009"},{"key":"ref16","article-title":"Socially guided machine learning","author":"thomaz","year":"2006"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2011.6005223"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref19","article-title":"Insights in reinforcement learning: formal analysis and empirical evaluation of temporal- difference learning algorithms","author":"van hasselt","year":"2011"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1115\/1.1634282"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0003-9993(03)00292-2"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-9030-5_5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.bioeng.6.040803.140103"},{"key":"ref6","first-page":"158","article-title":"New control strategies for neuroprosthetic systems","volume":"33","author":"crago","year":"1996","journal-title":"J Rehabil Res Dev"},{"key":"ref29","first-page":"59","author":"winter","year":"2005","journal-title":"Biomechanics and Motor Control of Human Movement"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/86.559345"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3109\/10929080600740814"},{"key":"ref7","article-title":"Feedback control of a high level upper extremity neuroprosthesis","author":"blana","year":"2008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awt262"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2014.2324825"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/sj.sc.3102091"},{"key":"ref20","first-page":"1017","article-title":"Improving elevator performance using reinforcement learning","volume":"8","author":"crites","year":"1996","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-004-0485-3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICORR.2011.5975338"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s004220050325"},{"key":"ref23","first-page":"165","article-title":"Application of the actor-critic architecture to functional electrical stimulation control of a human arm","author":"thomas","year":"0","journal-title":"Proc 21st Annu Conf Innovat Appl Artif Intell"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1098\/rspb.1938.0050"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbiomech.2009.12.017"}],"container-title":["IEEE Transactions on Human-Machine Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221037\/7567604\/07478097.pdf?arnumber=7478097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:42:38Z","timestamp":1641987758000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7478097\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10]]},"references-count":40,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/thms.2016.2558630","relation":{},"ISSN":["2168-2291","2168-2305"],"issn-type":[{"value":"2168-2291","type":"print"},{"value":"2168-2305","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,10]]}}}