{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T03:29:55Z","timestamp":1729654195018,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,8]]},"DOI":"10.1109\/devlrn.2015.7346130","type":"proceedings-article","created":{"date-parts":[[2015,12,8]],"date-time":"2015-12-08T17:20:27Z","timestamp":1449595227000},"page":"135-142","source":"Crossref","is-referenced-by-count":3,"title":["Diversity-driven selection of exploration strategies in multi-armed bandits"],"prefix":"10.1109","author":[{"given":"Fabien","family":"Benureau","sequence":"first","affiliation":[]},{"given":"Pierre-Yves","family":"Oudeyer","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.2307\/3214163"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/4235.735432"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2011.6037368"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1952-09620-8"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1080\/095400998116486"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-78761-7_17"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1037\/0012-1649.43.4.1045"},{"key":"ref34","article-title":"On learning how to learn learning strategies","author":"schmidhuber","year":"1994","journal-title":"Technical report Technical Report FKI-198-94"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)90047-7"},{"key":"ref11","first-page":"24","article-title":"On upper-confidence bound policies for nonstationary bandit problems","author":"garivier","year":"2008"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.ps.39.020188.000245"},{"key":"ref13","first-page":"74","author":"goldberg","year":"1987","journal-title":"Simple genetic algorithms and the minimal deceptive problem"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/105971239700500305"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1569901.1569918"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1126\/science.1223416"},{"article-title":"Stretching to learn: Ambiguous evidence and variability in preschoolers exploratory play","year":"2008","author":"gweon","key":"ref17"},{"key":"ref18","first-page":"1069","article-title":"Learning exploration strategies in model-based reinforcement learning","author":"hester","year":"0","journal-title":"International Foundation for Autonomous Agents and Multiagent Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2013.00016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF01588971"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5651385"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/EVCO_a_00048"},{"key":"ref3","first-page":"255","article-title":"Online choice of active learning algorithms","volume":"5","author":"baram","year":"2004","journal-title":"J Mach Learn Res"},{"journal-title":"Multi-armed bandits for intelligent tutoring systems (submitted)","year":"2015","author":"clement","key":"ref6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2478\/s13230-013-0110-z"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15844-5_34"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1016\/j.cognition.2011.03.003","article-title":"Where science starts: Spontaneous experiments in preschoolers' exploratory play","volume":"120","author":"claire","year":"2011","journal-title":"Cognition"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32375-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-014-0110-x"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398375"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/72.712153"},{"key":"ref22","first-page":"71","article-title":"Submodular function maximization","author":"krause","year":"2014","journal-title":"Practical Approaches to Hard Problems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2008.4640821"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1999.774079"},{"article-title":"Exploiting open-endedness to solve problems through the search for novelty","year":"0","author":"lehman","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50030-1"},{"key":"ref25","article-title":"The strategic student approach for lifelong exploration and learning","author":"lopes","year":"2012","journal-title":"In Proc ICDL-Epirob 2012"}],"event":{"name":"2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","start":{"date-parts":[[2015,8,13]]},"location":"Providence, RI, USA","end":{"date-parts":[[2015,8,16]]}},"container-title":["2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7332337\/7346087\/07346130.pdf?arnumber=7346130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T21:10:49Z","timestamp":1498252249000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7346130\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,8]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/devlrn.2015.7346130","relation":{},"subject":[],"published":{"date-parts":[[2015,8]]}}}