{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T02:40:18Z","timestamp":1778899218423,"version":"3.51.4"},"reference-count":18,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,3]]},"DOI":"10.1109\/adprl.2009.4927537","type":"proceedings-article","created":{"date-parts":[[2009,5,19]],"date-time":"2009-05-19T15:50:44Z","timestamp":1242748244000},"page":"137-144","source":"Crossref","is-referenced-by-count":20,"title":["The knowledge gradient algorithm for online subset selection"],"prefix":"10.1109","author":[{"given":"Ilya O.","family":"Ryzhov","sequence":"first","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Warren","family":"Powell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]}],"member":"263","reference":[{"key":"17","first-page":"437","article-title":"multi-armed bandit algorithms and empirical evaluation","author":"vermorel","year":"2005","journal-title":"Proceedings of 10th European Conference on Machine Learning"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1214\/074921706000001111"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963"},{"key":"16","author":"ryzhov","year":"2008","journal-title":"The Knowledge Gradient Algorithm for a General Class of Online Learning Problems"},{"key":"13","doi-asserted-by":"crossref","DOI":"10.1201\/9781420035933","author":"miller","year":"2002","journal-title":"Subset Selection in Regression"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273587"},{"key":"11","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4168.001.0001","author":"kaelbling","year":"1993","journal-title":"Learning in embedded systems"},{"key":"12","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1287\/moor.12.2.262","article-title":"multi-armed bandit problem: decomposition and computation.","volume":"12","author":"katehakis michael","year":"1987","journal-title":"Mathematics of Operations Research"},{"key":"3","author":"de groot","year":"1970","journal-title":"Optimal Statistical Decisions"},{"key":"2","article-title":"new myopic sequential sampling procedures","author":"chick","year":"2007","journal-title":"submitted for publication"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.48.1.80.12444"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1007\/s10888-006-9043-7"},{"key":"7","author":"gittins","year":"1989","journal-title":"Multi-armed Bandit Allocation Indices"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368181"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1137\/070693424"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/SIEDS.2004.239976"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1016\/0378-3758(95)00169-7"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1007\/BF02926410"}],"event":{"name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","location":"Nashville, TN, USA","start":{"date-parts":[[2009,3,30]]},"end":{"date-parts":[[2009,4,2]]}},"container-title":["2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4910084\/4927513\/04927537.pdf?arnumber=4927537","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,18]],"date-time":"2020-05-18T07:28:33Z","timestamp":1589786913000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4927537\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,3]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/adprl.2009.4927537","relation":{},"subject":[],"published":{"date-parts":[[2009,3]]}}}