{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T05:22:28Z","timestamp":1720416148198},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2018,9,1]],"date-time":"2018-09-01T00:00:00Z","timestamp":1535760000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"National Science Council, China","award":["NSC-100-2221-E-002-096"]},{"DOI":"10.13039\/501100003711","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","award":["MOST-105-2218-E-002-034","MOST-106-2627-E-002-001"],"id":[{"id":"10.13039\/501100003711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1109\/tcds.2017.2775621","type":"journal-article","created":{"date-parts":[[2017,11,23]],"date-time":"2017-11-23T19:11:03Z","timestamp":1511464263000},"page":"701-711","source":"Crossref","is-referenced-by-count":8,"title":["Active Learning on Service Providing Model: Adjustment of Robot Behaviors Through Human Feedback"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"http:\/\/orcid.org\/0000-0003-3572-5274","authenticated-orcid":false,"given":"Shih-Huan","family":"Tseng","sequence":"first","affiliation":[]},{"given":"Feng-Chih","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-6947-7646","authenticated-orcid":false,"given":"Li-Chen","family":"Fu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2007.907484"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1145\/1502650.1502700","article-title":"A Bayesian reinforcement learning approach for customizing human–robot interfaces","author":"atrash","year":"2009","journal-title":"Proc 13th Int Conf Intell User Interfaces"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2008.926867"},{"key":"ref13","first-page":"2491","article-title":"Robot self-preservation and adaptation to user preferences in game play, a preliminary study","author":"castro-gonz\u00e1lez","year":"2011","journal-title":"Proc IEEE Int Conf Robot Biomech (ROBIO)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980426"},{"key":"ref15","doi-asserted-by":"crossref","author":"puterman","year":"1994","journal-title":"Markov Decision Processes","DOI":"10.1002\/9780470316887"},{"key":"ref16","first-page":"213","article-title":"R-max—A general polynomial time algorithm for near-optimal reinforcement learning","volume":"3","author":"brafman","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.physbeh.2004.04.020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1152\/jn.1998.80.1.1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1126\/science.1077349"},{"key":"ref4","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1109\/ICRA.2011.5980323","article-title":"A POMDP framework for modelling human interaction with assistive robots","author":"taha","year":"2011","journal-title":"Proc IEEE Int Conf Robot Autom (ICRA)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509181"},{"key":"ref5","first-page":"318","article-title":"Bipedal walking energy minimization by reinforcement learning with evolving policy parameterization","author":"kormushev","year":"2011","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst (IROS)"},{"key":"ref8","first-page":"878","article-title":"Reinforcement learning from human reward: Discounting in episodic tasks","author":"knox","year":"2012","journal-title":"Proc 21st IEEE Int Symp Robot Human Interact Commun (RO-MAN)"},{"key":"ref7","first-page":"981","article-title":"Learning to navigate through crowded environments","author":"henry","year":"2010","journal-title":"Proc IEEE Int Conf Robot Autom (ICRA)"},{"key":"ref2","first-page":"4990","article-title":"Co-creation of human–robot interaction rules through response prediction and habituation\/dishabituation","author":"kuriyama","year":"2009","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst (IROS)"},{"key":"ref9","first-page":"1000","article-title":"Real-time interactive reinforcement learning for robots","author":"thomaz","year":"2005","journal-title":"AAAI Workshop on Human Comprehensible Machine Learning"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1561\/1100000005","article-title":"Human–robot interaction: A survey","author":"goodrich","year":"2007","journal-title":"Foundations Trends Human–Comput Interaction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1037\/a0020747"},{"key":"ref22","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1037\/0278-7393.10.4.598"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5547-y"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1037\/a0020747"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2000.885963"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1080\/09540091.2014.885294"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/8457402\/08119555.pdf?arnumber=8119555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T11:59:41Z","timestamp":1643198381000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8119555\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9]]},"references-count":26,"journal-issue":{"issue":"3"},"URL":"http:\/\/dx.doi.org\/10.1109\/tcds.2017.2775621","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,9]]}}}
