{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T04:13:04Z","timestamp":1746245584297,"version":"3.40.4"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,3]]},"DOI":"10.1109\/ciss.2014.6814158","type":"proceedings-article","created":{"date-parts":[[2014,5,16]],"date-time":"2014-05-16T22:41:30Z","timestamp":1400280090000},"page":"1-9","source":"Crossref","is-referenced-by-count":9,"title":["Prior-free and prior-dependent regret bounds for Thompson Sampling"],"prefix":"10.1109","author":[{"given":"Sebastien","family":"Bubeck","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Che-Yu Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Learning to Optimize Via Posterior Sampling","year":"2013","author":"russo","key":"13"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.2307\/2332286"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34106-9_18"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1952-09620-8"},{"key":"3","article-title":"Minimax policies for adversarial and stochastic bandits","author":"audibert","year":"2009","journal-title":"Proceedings of the 22nd Annual Conference on Learning Theory (COLT)"},{"journal-title":"Further Optimal Regret Bounds for Thompson Sampling","year":"2012","author":"agrawal","key":"2"},{"key":"1","article-title":"Analysis of thompson sampling for the multi-armed bandit problem","author":"agrawal","year":"2012","journal-title":"Proceedings of the 25th Annual Conference on Learning Theory (COLT)"},{"key":"10","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1111\/j.2517-6161.1979.tb01068.x","article-title":"Bandit processes and dynamic allocation indices","volume":"14","author":"gittins","year":"1979","journal-title":"Journal Royal Statistical Society Series B"},{"key":"7","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-04414-4_7","article-title":"Pure exploration in multi-armed bandits problems","author":"bubeck","year":"2009","journal-title":"Proceedings of the 20th International Conference on Algorithmic Learning Theory (ALT)"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1561\/2200000024"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"4","first-page":"2635","article-title":"Regret bounds and minimax policies under partial monitoring","volume":"11","author":"audibert","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"9","article-title":"An empirical evaluation of thompson sampling","author":"chapelle","year":"2011","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"8","article-title":"Bounded regret in stochastic multi-armed bandits","author":"bubeck","year":"2013","journal-title":"Proceedings of the 26th Annual Conference on Learning Theory (COLT)"}],"event":{"name":"2014 48th Annual Conference on Information Sciences and Systems (CISS)","start":{"date-parts":[[2014,3,19]]},"location":"Princeton, NJ, USA","end":{"date-parts":[[2014,3,21]]}},"container-title":["2014 48th Annual Conference on Information Sciences and Systems (CISS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6809375\/6814063\/06814158.pdf?arnumber=6814158","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T23:19:13Z","timestamp":1746227953000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6814158\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,3]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/ciss.2014.6814158","relation":{},"subject":[],"published":{"date-parts":[[2014,3]]}}}