{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T07:32:41Z","timestamp":1791444761281,"version":"4.3.3"},"reference-count":16,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2010,5,1]],"date-time":"2010-05-01T00:00:00Z","timestamp":1272672000000},"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. Inform. Theory"],"published-print":{"date-parts":[[2010,5]]},"DOI":"10.1109\/tit.2010.2043762","type":"journal-article","created":{"date-parts":[[2010,4,26]],"date-time":"2010-04-26T17:35:55Z","timestamp":1272303355000},"page":"2441-2454","source":"Crossref","is-referenced-by-count":15,"title":["Universal Reinforcement Learning"],"prefix":"10.1109","volume":"56","author":[{"given":"Vivek F.","family":"Farias","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ciamac C.","family":"Moallemi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Van Roy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsachy","family":"Weissman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","volume":"2","author":"bertsekas","year":"2006","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1981.1056331"},{"key":"ref12","author":"martinian","year":"2000","journal-title":"RoShamBo and Data Compression"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-5320-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/18.144706"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/18.382012"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref4","first-page":"660","article-title":"reinforcement learning in pomdps without resets","author":"even-dar","year":"2005","journal-title":"Proc 19th Int Joint Conf Artif Intell (IJCAI)"},{"key":"ref3","first-page":"260","article-title":"near-optimal reinforcement learning in polynomial time","author":"kearns","year":"1998","journal-title":"Proc 15th Int Conf Mach Learn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2002.1013135"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1183907.1183911"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2002.1003834"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/18.720534"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1978.1055934"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.880067"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/234752.234753"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/18\/5452181\/05452185.pdf?arnumber=5452185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T01:01:02Z","timestamp":1633914062000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5452185\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,5]]},"references-count":16,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tit.2010.2043762","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"value":"0018-9448","type":"print"},{"value":"1557-9654","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,5]]}}}