{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:23:58Z","timestamp":1780637038090,"version":"3.54.1"},"reference-count":87,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","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":"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\/501100004410","name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu","doi-asserted-by":"publisher","award":["217E040"],"award-info":[{"award-number":["217E040"]}],"id":[{"id":"10.13039\/501100004410","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Higher Education Commission"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2022,10,1]]},"DOI":"10.1109\/taffc.2022.3190233","type":"journal-article","created":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T19:37:49Z","timestamp":1657741069000},"page":"1840-1853","source":"Crossref","is-referenced-by-count":17,"title":["Training Socially Engaging Robots: Modeling Backchannel Behaviors with Batch Reinforcement Learning"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8786-1871","authenticated-orcid":false,"given":"Nusrah","family":"Hussain","sequence":"first","affiliation":[{"name":"KUIS AI Lab., College of Engineering, Koç University, Istanbul, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2715-2368","authenticated-orcid":false,"given":"Engin","family":"Erzin","sequence":"additional","affiliation":[{"name":"KUIS AI Lab., College of Engineering, Koç University, Istanbul, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"T. Metin","family":"Sezgin","sequence":"additional","affiliation":[{"name":"KUIS AI Lab., College of Engineering, Koç University, Istanbul, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7515-3138","authenticated-orcid":false,"given":"Yucel","family":"Yemez","sequence":"additional","affiliation":[{"name":"KUIS AI Lab., College of Engineering, Koç University, Istanbul, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85483-8_20"},{"key":"ref72","first-page":"1","article-title":"Engagement capabilities for ECAs","author":"peters","year":"2005","journal-title":"Proc AAMAS Workshop Creating Bonds ECAs"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16202-2_11"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2663241"},{"key":"ref76","first-page":"1","article-title":"Deep recurrent Q-learning for partially observable MDPs","volume":"7","author":"hausknecht","year":"2015","journal-title":"CoRR"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/1734454.1734580"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-59"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.34"},{"key":"ref78","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref79","article-title":"Empirical study of off-policy policy evaluation for reinforcement learning","author":"voloshin","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2019.04.008"},{"key":"ref32","first-page":"465","article-title":"Defining socially assistive robotics","author":"feil-seifer","year":"2005","journal-title":"Proc 9th Int Conf Rehabil Robot"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-014-0242-2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-013-0178-y"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-009-9092-y"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-18184-9_32"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2013.744"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1753326.1753567"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5229-0"},{"key":"ref61","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018","journal-title":"Proc Conf Robot Learn"},{"key":"ref63","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"levine","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aat5954"},{"key":"ref64","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","author":"fujimoto","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref65","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume":"33","author":"kumar","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref66","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05204-1_21"},{"key":"ref67","first-page":"2160","article-title":"A theory of regularized markov decision processes","author":"geist","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref68","first-page":"163","article-title":"Engagement rewarded actor-critic with conservative Q-learning for speech-driven laughter backchannel generation","author":"bayramo?lu","year":"2021","journal-title":"Proc Int Conf Multimodal Interact"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.08.018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(02)00372-X"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.2044797"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2017.8172330"},{"key":"ref22","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9914"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2521"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925443"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3242976"},{"key":"ref51","article-title":"End-to-end offline goal-oriented dialog policy learning via policy gradient","author":"zhou","year":"2017"},{"key":"ref59","article-title":"BADGR: An autonomous self-supervised learning-based navigation system","author":"kahn","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159687"},{"key":"ref57","first-page":"3632","article-title":"Off-policy evaluation for slate recommendation","author":"swaminathan","year":"2017","journal-title":"Proc Adv Neural Informat Process Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2020.1831925"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12625"},{"key":"ref52","article-title":"Way off-policy batch deep reinforcement learning of implicit human preferences in dialog","author":"jaques","year":"2019"},{"key":"ref10","first-page":"1","article-title":"Gaze direction as a back-channel inviting cue in dialogue","author":"hjalmarsson","year":"2012","journal-title":"Proc Workshop Realtime Conversational Virtual Agents"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2017.00047"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1395"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-31053-4_7"},{"key":"ref13","first-page":"11","article-title":"Back-channelling: The use of yeah and mm to portray engaged listenership","volume":"4","author":"lambertz","year":"2011","journal-title":"Griffith Working Papers in Pragmatics and Intercultural Communication"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/01638538809544706"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1037\/0012-1649.21.3.473"},{"key":"ref82","first-page":"747","article-title":"The Furhat social companion talking head","author":"al moubayed","year":"2013","journal-title":"Proc 14th Annu Conf Int Speech Commun Assoc"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-2166(99)00109-5"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2016.7840682"},{"key":"ref17","first-page":"567","article-title":"On getting a word in edgewise","author":"yngve","year":"1970","journal-title":"Proc Chicago Linguistics Soc 6th Meeting"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-014-0227-1"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843613500059"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-018-0488-1"},{"key":"ref80","article-title":"Behaviour policy estimation in off-policy policy evaluation: Calibration matters","author":"raghu","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1515\/jaiscr-2015-0018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2658861.2658881"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-015-0298-7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/asi.20801"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2005.03.005"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.55613\/jeet.v26i1.55"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/1121241.1121249"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3234149"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.05.023"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-301"},{"key":"ref46","first-page":"135","article-title":"Modelling empathy in social robotic companions","author":"leite","year":"2011","journal-title":"Proc of the Conf on User Modeling Adaption and Personalization"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.02.002"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.7210\/jrsj.24.820"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989193"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-744"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2522848.2522866"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2051874"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2215"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165369\/9964459\/09829283.pdf?arnumber=9829283","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T19:40:27Z","timestamp":1671478827000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9829283\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,1]]},"references-count":87,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2022.3190233","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,1]]}}}