{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:17:05Z","timestamp":1791487025022,"version":"4.3.4"},"reference-count":18,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018AAA0100905"],"award-info":[{"award-number":["2018AAA0100905"]}]},{"DOI":"10.13039\/501100008048","name":"program B for Outstanding Ph.D. candidate of Nanjing University","doi-asserted-by":"publisher","award":["201801B051"],"award-info":[{"award-number":["201801B051"]}],"id":[{"id":"10.13039\/501100008048","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1109\/tnnls.2020.2995920","type":"journal-article","created":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T21:14:26Z","timestamp":1591046066000},"page":"2285-2291","source":"Crossref","is-referenced-by-count":8,"title":["An Optimal Algorithm for the Stochastic Bandits While Knowing the Near-Optimal Mean Reward"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5379-9539","authenticated-orcid":false,"given":"Shangdong","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2488-1813","authenticated-orcid":false,"given":"Yang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24412-4_15"},{"key":"ref12","first-page":"122","article-title":"Bounded regret in stochastic multi-armed bandits","author":"bubeck","year":"2013","journal-title":"Proc COLT"},{"key":"ref13","first-page":"638","article-title":"Prior-free and prior-dependent regret bounds for Thompson sampling","author":"bubeck","year":"2013","journal-title":"Proc NIPS"},{"key":"ref14","first-page":"1690","article-title":"An optimal algorithm for the thresholding bandit problem","author":"locatelli","year":"2016","journal-title":"Proc ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40501-3_45"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2013.6810607"},{"key":"ref17","first-page":"54","article-title":"Nonparametric bandits with covariates","author":"rigollet","year":"2010","journal-title":"Proc COLT"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2600243"},{"key":"ref3","first-page":"2660","article-title":"Thompson sampling for stochastic bandits with graph feedback","author":"tossou","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2854796"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2818742"},{"key":"ref8","first-page":"809","article-title":"Efficient regret bounds for online bid optimisation in budget-limited sponsored search auctions","author":"tran-thanh","year":"2014","journal-title":"Proc UAI"},{"key":"ref7","first-page":"1871","article-title":"Optimal regret minimization in posted-price auctions with strategic buyers","author":"mohri","year":"2014","journal-title":"Proc NIPS"},{"key":"ref2","first-page":"1587","article-title":"Anytime optimal algorithms in stochastic multi-armed bandits","author":"degenne","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1952-09620-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2422436.2422465"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9420773\/09104874.pdf?arnumber=9104874","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:16Z","timestamp":1652194396000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9104874\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5]]},"references-count":18,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.2995920","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5]]}}}