{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T03:10:52Z","timestamp":1772766652177,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2018,12,1]],"date-time":"2018-12-01T00:00:00Z","timestamp":1543622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/legalcode"}],"funder":[{"name":"EU-funded Project BabyRobot","award":["687831"],"award-info":[{"award-number":["687831"]}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004100","name":"Labex","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004100","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004794","name":"Centre National de la Recherche Scientifique","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004794","id-type":"DOI","asserted-by":"publisher"}]},{"name":"EU-funded Project BabyRobot","award":["687831"],"award-info":[{"award-number":["687831"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/tcds.2018.2843122","type":"journal-article","created":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T18:37:57Z","timestamp":1530815877000},"page":"881-893","source":"Crossref","is-referenced-by-count":35,"title":["Robot Fast Adaptation to Changes in Human Engagement During Simulated Dynamic Social Interaction With Active Exploration in Parameterized Reinforcement Learning"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2515-1046","authenticated-orcid":false,"given":"Mehdi","family":"Khamassi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3358-7488","authenticated-orcid":false,"given":"George","family":"Velentzas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Theodore","family":"Tsitsimis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1545-9191","authenticated-orcid":false,"given":"Costas","family":"Tzafestas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IntelliSys.2017.8324365"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref32","first-page":"1","article-title":"Online adaptation to perturbations in human engagement during human–robot interaction with parallel reinforcement learning processes","author":"tsitsimis","year":"2017","journal-title":"Proc MultiLearn Workshop 25th Eur Signal Process Conf"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2017.33"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/nn.2342"},{"key":"ref37","first-page":"784","article-title":"Discounted UCB","author":"kocsis","year":"2006","journal-title":"2nd Pascal Challenge Workshop"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms9096"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-444-62604-2.00022-8"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1088\/1748-3182\/7\/2\/025009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843613500059"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.2009.21401"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2559636.2559682"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-09435-9_33"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2010.5453163"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-016-0357-8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2017.2686487"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/asi.20801"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2011.00001"},{"key":"ref18","first-page":"1934","article-title":"Reinforcement learning with parameterized actions","author":"masson","year":"2016","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref19","article-title":"Deep reinforcement learning in parameterized action space","author":"hausknecht","year":"2015","journal-title":"arXiv 1511 04143"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3077"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2010.5453184"},{"key":"ref27","article-title":"On upper-confidence bound policies for non-stationary bandit problems","author":"garivier","year":"2008","journal-title":"Arxiv preprint arXiv 0805 3415"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.04.002"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2016.07.002"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"876","DOI":"10.1038\/nature04766","article-title":"Cortical substrates for exploratory decisions in humans","volume":"441","author":"daw","year":"2006","journal-title":"Nature"},{"key":"ref5","first-page":"97","article-title":"An architecture for fluid real-time conversational agents: Integrating incremental output generation and input processing","volume":"8","author":"kopp","year":"2014","journal-title":"J Multimodal User Interfaces"},{"key":"ref8","author":"tomasello","year":"2010","journal-title":"Origins of Human Communication"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-015-0298-7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1228716.1228752"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2012.00003"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/89.985544"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3389\/fnbeh.2015.00225"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/09540090600768658"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2005.03.005"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/DevLrn.2013.6652535"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.05.008"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2015.7344834"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-018-0147-8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23974-8_29"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2016.00008"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.03.007"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(02)00228-9"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1121241.1121249"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368199"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/8567843\/08404000.pdf?arnumber=8404000","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T04:40:38Z","timestamp":1643258438000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8404000\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":46,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2018.2843122","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12]]}}}