{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T09:24:54Z","timestamp":1730193894567,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1109\/acii.2019.8925443","type":"proceedings-article","created":{"date-parts":[[2019,12,27]],"date-time":"2019-12-27T13:44:34Z","timestamp":1577454274000},"page":"1-7","source":"Crossref","is-referenced-by-count":6,"title":["Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents"],"prefix":"10.1109","author":[{"given":"Nusrah","family":"Hussain","sequence":"first","affiliation":[]},{"given":"Engin","family":"Erzin","sequence":"additional","affiliation":[]},{"given":"T. Metin","family":"Sezgin","sequence":"additional","affiliation":[]},{"given":"Yucel","family":"Yemez","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref38","first-page":"881","article-title":"Fast nearest neighbor search through sparse random projections and voting","author":"hyv\u00f6nen","year":"0","journal-title":"Proceedings of the 2016 IEEE International Conference on Big Data (Big Data)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.08.018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.10.004"},{"key":"ref31","first-page":"375","article-title":"Recognizing engagement in human-robot interaction","author":"rich","year":"0","journal-title":"Human-Robot Interaction (HRI) 2010 5th ACM\/IEEE International Conference on"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2663263"},{"journal-title":"Behaviour policy estimation in off-policy policy evaluation Calibration matters","year":"2018","author":"raghu","key":"ref37"},{"key":"ref36","article-title":"Importance sampling for fair policy selection","author":"doroudi","year":"2017","journal-title":"Grantee Submission"},{"key":"ref35","first-page":"2139","article-title":"Data-efficient off-policy policy evaluation for reinforcement learning","author":"thomas","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1395"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2522848.2522890"},{"key":"ref12","article-title":"Deep recurrent q-learning for partially observable mdps","author":"hausknecht","year":"0","journal-title":"2015 AAAI Fall Symposium Series"},{"key":"ref13","first-page":"1077","article-title":"Offline policy evaluation across representations with applications to educational games","author":"mandel","year":"0","journal-title":"Proceedings of the 2014 international conference on Autonomous agents and multi-agent systems International Foundation for Autonomous Agents and Multiagent Systems"},{"key":"ref14","article-title":"Personalized ad recommendation systems for life-time value optimization with guarantees","author":"theocharous","year":"0","journal-title":"Twenty-Fourth International Joint Conference on Artificial Intelligence"},{"key":"ref15","first-page":"1671","article-title":"Adaptive treatment of epilepsy via batch-mode reinforcement learning","author":"guez","year":"2008","journal-title":"AAAI"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref18","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/978-3-642-27645-3_2","article-title":"Batch reinforcement learning","author":"lange","year":"2012","journal-title":"Reinforcement Learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152572"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-015-0298-7"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-31053-4_7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/asi.20801"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-013-0503-z"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157797"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2395123.2395128"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344688"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2940325"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2012.6178834"},{"key":"ref9","article-title":"Mind, hands, face and body: a goal and belief view of multimodal communication","author":"poggi","year":"2007","journal-title":"Weidler"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1007\/978-3-540-30301-5_59","article-title":"Social robots that interact with people","author":"breazeal","year":"2008","journal-title":"Springer Handbook of Robotics"},{"key":"ref20","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":"ref22","first-page":"317","article-title":"Neural fitted q iteration-first experiences with a data efficient neural reinforcement learning method","author":"riedmiller","year":"0","journal-title":"European Conference on Machine Learning"},{"key":"ref21","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989193"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803357"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.05.023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.7210\/jrsj.24.820"}],"event":{"name":"2019 8th International Conference on Affective Computing and Intelligent Interaction (ACII)","start":{"date-parts":[[2019,9,3]]},"location":"Cambridge, United Kingdom","end":{"date-parts":[[2019,9,6]]}},"container-title":["2019 8th International Conference on Affective Computing and Intelligent Interaction (ACII)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8911251\/8925431\/08925443.pdf?arnumber=8925443","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T20:22:50Z","timestamp":1658262170000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8925443\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/acii.2019.8925443","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}