{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T16:55:35Z","timestamp":1762102535693,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1109\/infocom41043.2020.9155362","type":"proceedings-article","created":{"date-parts":[[2020,8,4]],"date-time":"2020-08-04T22:29:35Z","timestamp":1596580175000},"page":"159-168","source":"Crossref","is-referenced-by-count":7,"title":["Exploring Best Arm with Top Reward-Cost Ratio in Stochastic Bandits"],"prefix":"10.1109","author":[{"given":"Zhida","family":"Qin","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,P. R. China"}]},{"given":"Xiaoying","family":"Gan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,P. R. China"}]},{"given":"Jia","family":"Liu","sequence":"additional","affiliation":[{"name":"Iowa State University,Department of Computer Science,Ames,IA,USA"}]},{"given":"Hongqiu","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,P. R. China"}]},{"given":"Haiming","family":"Jin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,P. R. China"}]},{"given":"Luoyi","family":"Fu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,P. R. China"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Best-arm identification in linear bandits","author":"soare","year":"2014","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/s18051445"},{"year":"2018","author":"zhou","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"ref10","article-title":"Pure exploration of multi-armed bandits with heavy-tailed payoffs","author":"yu","year":"2018","journal-title":"UAI"},{"key":"ref11","article-title":"On top-k selection in multi-armed bandits and hidden bipartite graphs","author":"cao","year":"2015","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Multi-bandit best arm identification","author":"gabillon","year":"2011","journal-title":"NeurIPS"},{"key":"ref13","article-title":"Best arm identification: a unified approach to fixed budget and fixed confidence","author":"gabillon","year":"2012","journal-title":"NeurIPS"},{"key":"ref14","article-title":"Best action selection in a stochastic environment","author":"xia","year":"2016","journal-title":"AAMAS"},{"key":"ref15","article-title":"Exploring k out of top ? fraction of arms in stochastic bandits","author":"ren","year":"2019","journal-title":"AISTATS"},{"key":"ref16","article-title":"Hoeffding races: accelerating model selection search for classification and function approximation","author":"maron","year":"1993","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2014.6814096"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04414-4_7"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1145\/1390156.1390241","article-title":"Empirical bernstein stopping","author":"mnih","year":"2008","journal-title":"ICML"},{"key":"ref28","first-page":"1283","article-title":"On identifying good options under combinatorially structured feedback in finite noisy environments","author":"wu","year":"2015","journal-title":"ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737461"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486279"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849327"},{"year":"2004","author":"madani","key":"ref6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2010.12.059"},{"key":"ref5","article-title":"Best arm identification in multi-armed bandits","author":"audibert","year":"2010","journal-title":"COLT"},{"key":"ref8","article-title":"PAC identification of a bandit arm relative to a reward quantile","author":"chaudhuri","year":"2017","journal-title":"AAAI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737654"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2866198"},{"key":"ref9","article-title":"Infinitely many-armed bandits with budget constraints","author":"li","year":"2017","journal-title":"AAAI"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45435-7_18"},{"key":"ref20","article-title":"Optimal PAC multiple arm identification with applications to crowdsourcing","author":"zhou","year":"2014","journal-title":"ICML"},{"key":"ref22","first-page":"1079","article-title":"Action elimination and stopping conditions for the multi-armed bandit and reinforcement learning problems","volume":"7","author":"even-dar","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","article-title":"Empirical bernstein bounds and sample variance penalization","author":"maurer","year":"2009","journal-title":"COLT"},{"key":"ref24","article-title":"Efficient selection of multiple bandit arms: theory and practice","author":"kalyanakrishnan","year":"2010","journal-title":"ICML"},{"key":"ref23","first-page":"1","article-title":"On the complexity of bestarm identification in multi-armed bandit models","volume":"17","author":"kaufmann","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref26","article-title":"Simple regret for infinitely many armed bandits","author":"carpentier","year":"2015","journal-title":"ICML"},{"key":"ref25","article-title":"Pac subset selection in stochastic multiarmed bandits","author":"kalyanakrishnan","year":"2012","journal-title":"ICML"}],"event":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications","start":{"date-parts":[[2020,7,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2020,7,9]]}},"container-title":["IEEE INFOCOM 2020 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9146503\/9155217\/09155362.pdf?arnumber=9155362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T18:54:29Z","timestamp":1732301669000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9155362\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/infocom41043.2020.9155362","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}