{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:59:53Z","timestamp":1766138393714,"version":"3.37.3"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003977","name":"Israel Science Foundation","doi-asserted-by":"publisher","award":["1782\/22"],"award-info":[{"award-number":["1782\/22"]}],"id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/tit.2023.3299460","type":"journal-article","created":{"date-parts":[[2023,7,28]],"date-time":"2023-07-28T17:30:29Z","timestamp":1690565429000},"page":"7160-7184","source":"Crossref","is-referenced-by-count":4,"title":["Multi-Armed Bandits With Self-Information Rewards"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6028-8892","authenticated-orcid":false,"given":"Nir","family":"Weinberger","sequence":"first","affiliation":[{"name":"Faculty of Electrical and Computer Engineering, Technion—Israel Institute of Technology, Haifa, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2087-1183","authenticated-orcid":false,"given":"Michal","family":"Yemini","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Bar-Ilan University, Ramat Gan, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"Combinatorial multi-armed bandit with general reward functions","volume":"29","author":"chen","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511921889"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746078"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2009.01.016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1978.1055912"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1561\/0100000004"},{"article-title":"Universal gambling schemes and the complexity measures of Kolmogorov and Chaitin","year":"1974","author":"cover","key":"ref14"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1214\/13-AOS1119"},{"key":"ref53","first-page":"26","article-title":"Regret minimization in heavy-tailed bandits","author":"agrawal","year":"2021","journal-title":"Proc Conf Learn Theory"},{"key":"ref52","first-page":"11269","article-title":"Distribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewards","author":"kagrecha","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3054344"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref10","first-page":"2998","article-title":"Near optimal exploration-exploitation in non-communicating Markov decision processes","author":"fruit","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1561\/2200000068"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1063\/5.0031844"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/01431160600647225"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3132635.3132649"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.11.023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2277869"},{"key":"ref50","first-page":"169","article-title":"Thompson sampling for complex online problems","volume":"1","author":"gopalan","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn (ICML)"},{"key":"ref46","first-page":"358","article-title":"Information directed sampling and bandits with heteroscedastic noise","volume":"75","author":"kirschner","year":"2018","journal-title":"Proc 31st Conf Learn Theory"},{"key":"ref45","article-title":"Learning to optimize via information-directed sampling","volume":"27","author":"russo","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/25.3-4.285"},{"key":"ref47","first-page":"2777","article-title":"Asymptotically optimal information-directed sampling","volume":"134","author":"kirschner","year":"2021","journal-title":"Proc 34th Conf Learn Theory"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00775"},{"key":"ref41","first-page":"2157","article-title":"Estimating the unseen: Improved estimators for entropy and other properties","volume":"26","author":"valiant","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2733537"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2412945"},{"key":"ref49","first-page":"1","article-title":"An information-theoretic analysis of Thompson sampling","volume":"17","author":"russo","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref8","first-page":"1563","article-title":"Near-optimal regret bounds for reinforcement learning","volume":"11","author":"jaksch","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1987.1104485"},{"key":"ref9","first-page":"35","article-title":"REGAL: A regularization based algorithm for reinforcement learning in weakly communicating MDPs","author":"bartlett","year":"2009","journal-title":"Proc UAI"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472588"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1100.0446"},{"key":"ref6","first-page":"2312","article-title":"Improved algorithms for linear stochastic bandits","volume":"24","author":"abbasi-yadkori","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"355","article-title":"Stochastic linear optimization under bandit feedback","author":"dani","year":"2008","journal-title":"Proc Conf Learn Theory (COLT)"},{"key":"ref40","first-page":"1","article-title":"Bayesian entropy estimation for binary spike train data using parametric prior knowledge","volume":"26","author":"archer","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2080452"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/rsa.10019"},{"key":"ref37","first-page":"1","article-title":"Entropy estimates from insufficient samplings","volume":"abs 307138","author":"grassberger","year":"2008","journal-title":"CoRR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2274515"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511581274"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1561\/2200000024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/089976603321780272"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1561\/0100000064"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT50566.2022.9834746"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210X.12108"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/e13122013"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206232"},{"journal-title":"Elements of Information Theory","year":"2006","author":"cover","key":"ref23"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623999"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431315"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196707"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/e22080845"},{"key":"ref64","first-page":"497","article-title":"A finite-time analysis of multi-armed bandits problems with Kullback–Leibler divergences","author":"maillard","year":"2011","journal-title":"Proc 24th Annu Conf Learn Theory"},{"key":"ref63","first-page":"67","article-title":"An asymptotically optimal bandit algorithm for bounded support models","author":"honda","year":"2010","journal-title":"Proc COLT"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/e15114909"},{"journal-title":"Probability and Computing Randomization and Probabilistic Techniques in Algorithms and Data Analysis","year":"2017","author":"mitzenmacher","key":"ref66"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCNC.2017.7876150"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2021.3081508"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/e12071765"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/ece3.1155"},{"key":"ref29","first-page":"397","article-title":"Using confidence bounds for exploitation-exploration trade-offs","volume":"3","author":"auer","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1214\/17-AOS1665"},{"key":"ref62","first-page":"359","article-title":"The KL-UCB algorithm for bounded stochastic bandits and beyond","author":"garivier","year":"2011","journal-title":"Proc 24th Annu Conf Learn Theory"},{"article-title":"Bandits games and clustering foundations","year":"2010","author":"bubeck","key":"ref61"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/18\/10288603\/10196497.pdf?arnumber=10196497","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T19:12:56Z","timestamp":1699297976000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10196497\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":67,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tit.2023.3299460","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"type":"print","value":"0018-9448"},{"type":"electronic","value":"1557-9654"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}