{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:34:26Z","timestamp":1773246866050,"version":"3.50.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"STI 2030 Major Projects","award":["2021ZD0200400"],"award-info":[{"award-number":["2021ZD0200400"]}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61925603"],"award-info":[{"award-number":["61925603"]}],"id":[{"id":"10.13039\/501100001809","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":[[2023,9]]},"DOI":"10.1109\/tnnls.2023.3295360","type":"journal-article","created":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T18:16:28Z","timestamp":1690913788000},"page":"5332-5341","source":"Crossref","is-referenced-by-count":10,"title":["A Thompson Sampling Algorithm With Logarithmic Regret for Unimodal Gaussian Bandit"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7675-2194","authenticated-orcid":false,"given":"Long","family":"Yang","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5056-0351","authenticated-orcid":false,"given":"Zhao","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]},{"given":"Zehong","family":"Hu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]},{"given":"Shasha","family":"Ruan","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4049-6181","authenticated-orcid":false,"given":"Gang","family":"Pan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1374376.1374475"},{"key":"ref12","first-page":"697","article-title":"Nearly tight bounds for the continuum-armed bandit problem","author":"kleinberg","year":"2004","journal-title":"Proc NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729392"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2009.2019797"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/414"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/66"},{"key":"ref11","first-page":"1377","article-title":"Fraud regulating policy for e-commerce via constrained contextual bandits","author":"hu","year":"2019","journal-title":"Proc AAMAS"},{"key":"ref10","first-page":"964","article-title":"Linear multi-resource allocation with semi-bandit feedback","volume":"28","author":"lattimore","year":"2015","journal-title":"Proc NeurIPS"},{"key":"ref32","author":"lattimore","year":"2018","journal-title":"Bandit Algorithms"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.electstud.2010.09.001"},{"key":"ref1","first-page":"41","article-title":"Unimodal bandits","author":"yu","year":"2011","journal-title":"Proc ICML"},{"key":"ref17","first-page":"359","article-title":"The KL-UCB algorithm for bounded stochastic bandits and beyond","author":"garivier","year":"2011","journal-title":"Proc COLT"},{"key":"ref16","article-title":"Unimodal bandits without smoothness","author":"combes","year":"2014","journal-title":"arXiv 1406 7447"},{"key":"ref19","first-page":"99","article-title":"Further optimal regret bounds for Thompson sampling","author":"agrawal","year":"2013","journal-title":"Proc AISIATS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1214\/13-AOS1119"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"ref26","first-page":"23","article-title":"Online learning with feedback graphs: Beyond bandits","volume":"40","author":"alon","year":"2015","journal-title":"Proc COLT"},{"key":"ref25","first-page":"1","article-title":"Leveraging side observations in stochastic bandits","author":"caron","year":"2012","journal-title":"Proc UAI"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17271"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00205"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20863"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11452"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1995.492488"},{"key":"ref29","article-title":"Controlling type confounding in ad hoc teamwork with instance-wise teammate feedback rectification","author":"xing","year":"2023","journal-title":"arXiv 2306 10944"},{"key":"ref8","first-page":"862","article-title":"Solving Bernoulli rank-one bandits with unimodal Thompson sampling","author":"trinh","year":"2020","journal-title":"Proc 31st Int Conf Algorithmic Learn Theory"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/25.3-4.285"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.49.10.1287.17315"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2006.08.008"},{"key":"ref3","volume":"1","author":"mas-colell","year":"1995","journal-title":"Microeconomic Theory"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10797"},{"key":"ref5","first-page":"521","article-title":"Unimodal bandits: Regret lower bounds and optimal algorithms","author":"combes","year":"2014","journal-title":"Proc ICML"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10237282\/10198752.pdf?arnumber=10198752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:26:03Z","timestamp":1695666363000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10198752\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":32,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3295360","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}