{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T11:17:53Z","timestamp":1773141473369,"version":"3.50.1"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"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":[[2019,3]]},"DOI":"10.1109\/hri.2019.8673234","type":"proceedings-article","created":{"date-parts":[[2019,3,25]],"date-time":"2019-03-25T22:51:27Z","timestamp":1553554287000},"page":"354-363","source":"Crossref","is-referenced-by-count":16,"title":["The Assistive Multi-Armed Bandit"],"prefix":"10.1109","author":[{"given":"Lawrence","family":"Chan","sequence":"first","affiliation":[]},{"given":"Dylan","family":"Hadfield-Menell","sequence":"additional","affiliation":[]},{"given":"Siddhartha","family":"Srinivasa","sequence":"additional","affiliation":[]},{"given":"Anca","family":"Dragan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref38","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.6648"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-5110-1_13"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1952-09620-8"},{"key":"ref37","first-page":"1025","article-title":"Point-based value iteration: An anytime algorithm for pomdps","volume":"3","author":"pineau","year":"2003","journal-title":"IJCAI"},{"key":"ref36","first-page":"1025","article-title":"Efficient bayes-adaptive reinforcement learning using sample-based search","author":"guez","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref35","first-page":"2164","article-title":"Monte-carlo planning in large pomdps","author":"silver","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2307\/1427934"},{"key":"ref27","first-page":"623","article-title":"The sample complexity of exploration in the multi-armed bandit problem","volume":"5","author":"mannor","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1214\/13-AOS1119"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7552(97)00016-0"},{"key":"ref1","first-page":"789","article-title":"Preference learning","author":"f\u00fcrnkranz","year":"2011","journal-title":"Encyclopedia of Machine Learning"},{"key":"ref20","author":"baron","year":"2000","journal-title":"Thinking and Deciding"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1111\/0002-9092.00099"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-207350-2.50012-9"},{"key":"ref24","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"ICML"},{"key":"ref23","author":"duan","year":"2016","journal-title":"R12 Fast reinforcement learning via slow reinforcement learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref50","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","author":"salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref51","first-page":"1638","article-title":"Taming the monster: A fast and simple algorithm for contextual bandits","author":"agarwal","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2016.7451754"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759036"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.2307\/2332286"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3171221.3171267"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1134707.1134712"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35311-6_9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-13129-0_28"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3368\/le.86.3.530"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1115\/1.3653115"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279964"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-015-7629-1_17"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2569096"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"ref6","author":"goel","year":"2009","journal-title":"Predicting user preference for movies using netflix database"},{"key":"ref5","first-page":"714","article-title":"Recommendation as classification: Using social and content-based information in recommendation","author":"basu","year":"1998","journal-title":"AAAI\/IAAI"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-012-0160-0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC.2018.8301647"},{"key":"ref49","author":"schulman","year":"2015","journal-title":"High-dimensional continuous control using generalized advantage estimation"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2012.VIII.025"},{"key":"ref46","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1063\/1.1699114"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2012.6315022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref42","first-page":"592","article-title":"On bayesian upper confidence bounds for bandit problems","author":"kaufmann","year":"2012","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2014.2307024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1002\/9781118596333.ch24"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1979.tb01068.x"}],"event":{"name":"2019 14th ACM\/IEEE International Conference on Human-Robot Interaction (HRI)","location":"Daegu, Korea (South)","start":{"date-parts":[[2019,3,11]]},"end":{"date-parts":[[2019,3,14]]}},"container-title":["2019 14th ACM\/IEEE International Conference on Human-Robot Interaction (HRI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8666012\/8673065\/08673234.pdf?arnumber=8673234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T20:20:44Z","timestamp":1658262044000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8673234\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/hri.2019.8673234","relation":{},"subject":[],"published":{"date-parts":[[2019,3]]}}}