{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T12:09:36Z","timestamp":1783339776385,"version":"3.54.6"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51809246"],"award-info":[{"award-number":["51809246"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2018QF003"],"award-info":[{"award-number":["ZR2018QF003"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3006254","type":"journal-article","created":{"date-parts":[[2020,7,2]],"date-time":"2020-07-02T20:27:41Z","timestamp":1593721661000},"page":"120757-120765","source":"Crossref","is-referenced-by-count":95,"title":["A Review on Interactive Reinforcement Learning From Human Social Feedback"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8019-9758","authenticated-orcid":false,"given":"Jinying","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3881-7417","authenticated-orcid":false,"given":"Zhen","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3191-6818","authenticated-orcid":false,"given":"Randy","family":"Gomez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4979-2083","authenticated-orcid":false,"given":"Keisuke","family":"Nakamura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6826-4721","authenticated-orcid":false,"given":"Bo","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1728-5711","authenticated-orcid":false,"given":"Guangliang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2018.8525837"},{"key":"ref39","first-page":"5","article-title":"Combining manual feedback with subsequent MDP reward signals for reinforcement learning","volume":"1","author":"knox","year":"2010","journal-title":"Proc 9th Int Conf Auton Agents Multiagent Syst"},{"key":"ref38","first-page":"3366","article-title":"Policy shaping with human teachers","author":"cederborg","year":"2015","journal-title":"Proc 24th Int Joint Conf Artif Intell"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.09.009"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/566570.566597"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/DevLrn.2012.6400849"},{"key":"ref37","first-page":"2625","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","author":"griffith","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","article-title":"Deep reinforcement learning from policy-dependent human feedback","author":"arumugam","year":"2019","journal-title":"arXiv 1902 04257"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2011.6005223"},{"key":"ref60","first-page":"135","article-title":"Modelling empathy in social robotic companions","author":"leite","year":"2007","journal-title":"Proc Int Conf User Modeling Adaptation and Personalization"},{"key":"ref62","article-title":"Conversational transfer learning for emotion recognition","author":"hazarika","year":"2019","journal-title":"arXiv 1910 04980"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2007.4354072"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"ref28","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"Proc ICML"},{"key":"ref64","first-page":"1","article-title":"Transparency and socially guided machine learning","author":"thomaz","year":"2006","journal-title":"Proc of 5th IEEE Int Conf on Development and Learning (ICDL)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-02675-6_46"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543752"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2005.1545011"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2015.03.009"},{"key":"ref67","first-page":"617","article-title":"Integrating reinforcement learning with human demonstrations of varying ability","volume":"2","author":"taylor","year":"2011","journal-title":"Proc 10th Int Conf Auton Agents Multiagent Syst"},{"key":"ref68","first-page":"3352","article-title":"Reinforcement learning from demonstration through shaping","author":"brys","year":"2015","journal-title":"Proc Int Joint Conf Artif Intell (IJCAI)"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/860575.860614"},{"key":"ref2","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref20","first-page":"1","article-title":"An experimental study of advice in sequential decision-making under uncertainty","author":"benavent","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/882"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2019.2912447"},{"key":"ref24","article-title":"Socially intelligent autonomous agents that learn from human reward","author":"li","year":"2016"},{"key":"ref23","article-title":"Learning from human-generated reward","author":"knox","year":"2012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16952-6_49"},{"key":"ref25","first-page":"1","article-title":"Deep tamer: Interactive agent shaping in high-dimensional state spaces","author":"warnell","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-020-09447-w"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460937"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3242976"},{"key":"ref58","first-page":"2259","article-title":"Real-time adaptation of a robotic joke teller based on human social signals","author":"weber","year":"2018","journal-title":"Proc 7th Int Conf Auton Agents Multiagent Syst"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/568513.568514"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759137"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2013.2291714"},{"key":"ref54","first-page":"184","article-title":"A multi-agent system for programming robotic agents by human demonstration","author":"voyles","year":"1998","journal-title":"Proc AI Manuf Res Planning Workshop"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2000.871479"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1106"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-015-9283-7"},{"key":"ref40","first-page":"475","article-title":"Reinforcement learning from simultaneous human and MDP reward","volume":"1","author":"knox","year":"2012","journal-title":"Proc 11th Int Conf Auton Agents Multiagent Syst"},{"key":"ref12","first-page":"2285","article-title":"Interactive learning from policy-dependent human feedback","volume":"70","author":"macglashan","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref13","author":"lieberman","year":"2001","journal-title":"Your Wish Is My Command Programming by Example"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/880"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114730"},{"key":"ref17","first-page":"1","article-title":"Guiding a reinforcement learner with natural language advice: Initial results in RoboCup soccer","author":"kuhlmann","year":"2004","journal-title":"Proceedings of the AAAI Workshop on Supervisory Control of Learning and Adaptive Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/331"},{"key":"ref19","article-title":"Learning to understand goal specifications by modelling reward","author":"bahdanau","year":"2018","journal-title":"arXiv 1806 01946"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/375735.376334"},{"key":"ref3","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":"ref6","first-page":"1000","article-title":"Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance","volume":"6","author":"thomaz","year":"2006","journal-title":"Proc AAAI"},{"key":"ref5","first-page":"819","article-title":"Giving advice about preferred actions to reinforcement learners via knowledge-based kernel regression","author":"maclin","year":"1999","journal-title":"Proc Nat Conf Artif Intell"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICORR.2011.5975338"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1228716.1228725"},{"key":"ref49","first-page":"3951","article-title":"Affective personalization of a social robot tutor for children’s second language skills","author":"gordon","year":"2016","journal-title":"Proc AAAI"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref46","first-page":"385","article-title":"Learning behavior-selection by emotions and cognition in a multi-goal robot task","volume":"4","author":"gadanho","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-015-9308-2"},{"key":"ref48","article-title":"Face valuing: Training user interfaces with facial expressions and reinforcement learning","author":"veeriah","year":"2016","journal-title":"arXiv 1606 02807"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72348-6_6"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-015-0259-2"},{"key":"ref41","article-title":"DQN-TAMER: Human-in-the-Loop reinforcement learning with intractable feedback","author":"arakawa","year":"2018","journal-title":"arXiv 1810 11748"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2006.314459"},{"key":"ref43","first-page":"1","article-title":"Real-time interactive reinforcement learning for robots","author":"thomaz","year":"2005","journal-title":"AAAI Workshop on Human Comprehensible Machine Learning"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09131765.pdf?arnumber=9131765","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:53:04Z","timestamp":1639770784000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9131765\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3006254","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}