{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T20:50:18Z","timestamp":1782334218615,"version":"3.54.5"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62571347"],"award-info":[{"award-number":["62571347"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Low-Altitude Airspace Strategic Program Portfolio","award":["Z25306102"],"award-info":[{"award-number":["Z25306102"]}]},{"DOI":"10.13039\/501100020785","name":"Shenzhen Research Institute of Big Data","doi-asserted-by":"publisher","award":["J00120260001"],"award-info":[{"award-number":["J00120260001"]}],"id":[{"id":"10.13039\/501100020785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tsp.2026.3695892","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T19:37:43Z","timestamp":1779478663000},"page":"2434-2447","source":"Crossref","is-referenced-by-count":1,"title":["Optimistic Thompson Sampling for No-Regret Learning in Unknown Games"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2937-4687","authenticated-orcid":false,"given":"Yingru","family":"Li","sequence":"first","affiliation":[{"name":"Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3923-056X","authenticated-orcid":false,"given":"Wenqiang","family":"Pu","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4823-1000","authenticated-orcid":false,"given":"Hao","family":"Liang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3995-914X","authenticated-orcid":false,"given":"Zhi-Quan","family":"Luo","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tsp.2026.3695892"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2169251"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2008.080904"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2011.2144585"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2010.03.090084"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1504"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/1468-0262.00153"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398375"},{"key":"ref9","article-title":"Incomplete information and internal regret in prediction of individual sequences","author":"Stoltz","year":"2005"},{"key":"ref10","first-page":"613","article-title":"\u201cEfficient learning by implicit exploration in bandit problems with side observations,\u201d","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Koc\u00e1k","year":"2014"},{"key":"ref11","first-page":"3168","article-title":"\u201cExplore no more: Improved high-probability regret bounds for non-stochastic bandits,\u201d","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Neu","year":"2015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04623-4_12"},{"key":"ref14","article-title":"Solving large imperfect information games using CFR+","author":"Tammelin","year":"2014"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2690"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2973963"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2020.1051"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3555971"},{"key":"ref19","first-page":"911","article-title":"\u201cA near-optimal high-probability swap-regret upper bound for multi-agent bandits in unknown general-sum games,\u201d","volume-title":"Proc. Uncertainty Artif. Intell","author":"Huang","year":"2023"},{"key":"ref20","first-page":"679","article-title":"\u201cMultiplayer bandit learning, from competition to cooperation,\u201d","volume-title":"Proc. Conf. Learn. Theory","author":"Br\u00e2nzei","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-024-06336-3"},{"key":"ref22","first-page":"279","article-title":"\u201cMatrix games with bandit feedback,\u201d","volume-title":"Proc. Uncertainty Artif. Intell.","author":"O\u2019Donoghue","year":"2021"},{"key":"ref23","first-page":"38674","article-title":"Competing for shareable arms in multi-player multi-armed bandits","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2023"},{"key":"ref24","first-page":"13624","article-title":"No-regret learning in unknown games with correlated payoffs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Sessa","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1561\/9781680834710"},{"key":"ref26","first-page":"1988","article-title":"Old dog learns new tricks: Randomized UCB for bandit problems","volume-title":"Proc. 23rd Int. Conf. Artif. Intell. Statist., Ser. Mach. Learn. Res.","volume":"108","author":"Vaswani","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1137\/21M140924X"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2557"},{"key":"ref29","article-title":"HyperDQN: A randomized exploration method for deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2022"},{"key":"ref30","article-title":"Efficient and scalable reinforcement learning via hypermodel","volume-title":"Proc. Workshop Adaptive Exp. Des. Act. Learn. Real World (NeurIPS)","author":"Li","year":"2023"},{"key":"ref31","article-title":"HyperAgent: A simple, scalable, efficient and provable reinforcement learning framework for complex environments","author":"Li","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2021.0317"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref34","article-title":"Gaussian process optimization in the bandit setting: No regret and experimental design","author":"Srinivas","year":"2009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.9.3.183"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/11345506\/11534112.pdf?arnumber=11534112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T19:52:11Z","timestamp":1782330731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11534112\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/tsp.2026.3695892","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}