{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T08:47:51Z","timestamp":1774946871762,"version":"3.50.1"},"reference-count":22,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2014,3,1]],"date-time":"2014-03-01T00:00:00Z","timestamp":1393632000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2014,3]]},"DOI":"10.1109\/tac.2013.2292137","type":"journal-article","created":{"date-parts":[[2014,1,31]],"date-time":"2014-01-31T17:37:55Z","timestamp":1391189875000},"page":"676-691","source":"Crossref","is-referenced-by-count":15,"title":["Online Markov Decision Processes Under Bandit Feedback"],"prefix":"10.1109","volume":"59","author":[{"given":"Gergely","family":"Neu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andras","family":"Gyorgy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Csaba","family":"Szepesvari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andras","family":"Antos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1563","article-title":"Near-optimal regret bounds for reinforcement learning","volume":"99","author":"jaksch","year":"2010","journal-title":"J Mach Learning Res"},{"key":"ref11","first-page":"793","author":"kakade","year":"2010","journal-title":"Advances in Neural Information Processing Systems 22"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2011.12.027"},{"key":"ref13","first-page":"231","article-title":"The online loop-free stochastic shortest-path problem","author":"neu","year":"2010","journal-title":"Proc 10th Annu Conf Learning Theory"},{"key":"ref14","first-page":"805","article-title":"The adversarial stochastic shortest path problem with unknown transition probabilities","volume":"22","author":"neu","year":"2012","journal-title":"Proc Int Conf Artificial Intelligence Statistics"},{"key":"ref15","author":"neu","year":"2013","journal-title":"The Online Loop-Free Stochastic Shortest-Path Problem"},{"key":"ref16","first-page":"1804","article-title":"Online Markov decision processes under bandit feedback","author":"neu","year":"2011","journal-title":"Advances in Neural Information Processing Systems 23"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref18","first-page":"2752","author":"rakhlin","year":"2012","journal-title":"Advances in Neural Information Processing Systems 24"},{"key":"ref19","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2004.833339"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-69082-7"},{"key":"ref6","first-page":"401","author":"even-dar","year":"2005","journal-title":"Advances in Neural Information Processing Systems 17"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921"},{"key":"ref8","first-page":"2369","article-title":"The on-line shortest path problem under partial monitoring","volume":"8","author":"gy\ufffdrgy","year":"2007","journal-title":"J Mach Learning Res"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1090.0396"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398375"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2010.04.007"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/090752948"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2009.5400662"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1090.0397"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/GAMENETS.2009.5137416"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/6744666\/06675002.pdf?arnumber=6675002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,24]],"date-time":"2022-03-24T19:59:06Z","timestamp":1648151946000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6675002\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,3]]},"references-count":22,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tac.2013.2292137","relation":{},"ISSN":["0018-9286","1558-2523"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,3]]}}}