{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T22:44:20Z","timestamp":1753051460749,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,4]]},"DOI":"10.1109\/adprl.2011.5967348","type":"proceedings-article","created":{"date-parts":[[2011,8,4]],"date-time":"2011-08-04T01:40:00Z","timestamp":1312422000000},"page":"32-39","source":"Crossref","is-referenced-by-count":8,"title":["Active learning for personalizing treatment"],"prefix":"10.1109","author":[{"given":"Kun","family":"Deng","sequence":"first","affiliation":[]},{"given":"Joelle","family":"Pineau","sequence":"additional","affiliation":[]},{"given":"Susan","family":"Murphy","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM200005183422001"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/sim.3109"},{"key":"ref30","first-page":"1671","article-title":"Adaptive treatment of epilepsy via batch-mode reinforcement learning","author":"guez","year":"2008","journal-title":"Proceedings of the Twentieth Innovative Applications of Artificial Intelligence Conference"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993277"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1177009939"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007330508534"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/500156.500159"},{"key":"ref14","first-page":"898","article-title":"Software testing by active learning for commercial games","author":"xiao","year":"2005","journal-title":"AAAI"},{"key":"ref15","first-page":"647","article-title":"Active learning for parameter estimation in bayesian networks","author":"tong","year":"2001","journal-title":"In NIPS"},{"key":"ref16","first-page":"255","article-title":"Online choice of active learning algorithms","volume":"5","author":"bararn","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-27819-1_46"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1089827.1089829"},{"key":"ref19","first-page":"1655","article-title":"Active learning with feedback on features and instances","volume":"7","author":"raghavan","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/sim.1920"},{"key":"ref4","first-page":"213","article-title":"R-max-a general polynomial time algorithm for near-optimal reinforcement learning","volume":"3","author":"brafman","year":"2003","journal-title":"The Journal of Machine Learning Research"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00389"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/1740774508091815"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.drugalcdep.2006.09.008"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390194"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/1740774510373120"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/1740774509104992"},{"key":"ref2","first-page":"943","article-title":"A Bayesian framework for reinforcement learning","author":"strens","year":"2000","journal-title":"Machine Learning-International Workshop Then Conference"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1007\/978-3-540-87987-9_25","article-title":"Active learning in Multi-armed Bandits","author":"antos","year":"2008","journal-title":"Proceedings of International Conference on Algorithmic Learning Theory"},{"journal-title":"Efficient exploration in reinforcement learning (Technical Report CS-92–102)","year":"1992","author":"thrun","key":"ref1"},{"key":"ref20","first-page":"463","article-title":"Bandit-based algorithms for budgeted learning","author":"deng","year":"2008","journal-title":"Data Mining 2007 ICDM 2007 Seventh IEEE International Conference on"},{"journal-title":"Active Learning Literature Survey","year":"2009","author":"settles","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04414-4_7"},{"journal-title":"Active learning for logistic regression","year":"2005","author":"schein","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/wics.100"},{"journal-title":"All of Statistics A Concise Course in Statistical Inference","year":"2003","author":"wasserman","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143980"}],"event":{"name":"2011 Ieee Symposium On Adaptive Dynamic Programming And Reinforcement Learning","start":{"date-parts":[[2011,4,11]]},"location":"Paris, France","end":{"date-parts":[[2011,4,15]]}},"container-title":["2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5958170\/5967347\/05967348.pdf?arnumber=5967348","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T04:11:40Z","timestamp":1497931900000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5967348\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/adprl.2011.5967348","relation":{},"subject":[],"published":{"date-parts":[[2011,4]]}}}