{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T05:20:50Z","timestamp":1784784050387,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T00:00:00Z","timestamp":1709510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,4]]},"DOI":"10.1145\/3616855.3635833","type":"proceedings-article","created":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T18:18:12Z","timestamp":1709576292000},"page":"636-644","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Long-Term Value of Exploration: Measurements, Findings and Algorithms"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9207-1719","authenticated-orcid":false,"given":"Yi","family":"Su","sequence":"first","affiliation":[{"name":"Google Deepmind, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6239-3999","authenticated-orcid":false,"given":"Xiangyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Google, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0236-3562","authenticated-orcid":false,"given":"Elaine Ya","family":"Le","sequence":"additional","affiliation":[{"name":"Google, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1248-1012","authenticated-orcid":false,"given":"Liang","family":"Liu","sequence":"additional","affiliation":[{"name":"Google, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3849-5523","authenticated-orcid":false,"given":"Yuening","family":"Li","sequence":"additional","affiliation":[{"name":"Google, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7696-7732","authenticated-orcid":false,"given":"Haokai","family":"Lu","sequence":"additional","affiliation":[{"name":"Google Deepmind, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1111-5252","authenticated-orcid":false,"given":"Benjamin","family":"Lipshitz","sequence":"additional","affiliation":[{"name":"Google, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8891-3392","authenticated-orcid":false,"given":"Sriraj","family":"Badam","sequence":"additional","affiliation":[{"name":"Google, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0593-7345","authenticated-orcid":false,"given":"Lukasz","family":"Heldt","sequence":"additional","affiliation":[{"name":"Google, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7545-4410","authenticated-orcid":false,"given":"Shuchao","family":"Bi","sequence":"additional","affiliation":[{"name":"Google, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3230-5338","authenticated-orcid":false,"given":"Ed H.","family":"Chi","sequence":"additional","affiliation":[{"name":"Google Deepmind, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7408-9623","authenticated-orcid":false,"given":"Cristos","family":"Goodrow","sequence":"additional","affiliation":[{"name":"Google, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0425-1177","authenticated-orcid":false,"given":"Su-Lin","family":"Wu","sequence":"additional","affiliation":[{"name":"Google, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9200-270X","authenticated-orcid":false,"given":"Lexi","family":"Baugher","sequence":"additional","affiliation":[{"name":"Google, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7342-9022","authenticated-orcid":false,"given":"Minmin","family":"Chen","sequence":"additional","affiliation":[{"name":"Google Deepmind, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,3,4]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Improved algorithms for linear stochastic bandits. Advances in neural information processing systems 24","author":"Abbasi-Yadkori Yasin","year":"2011","unstructured":"Yasin Abbasi-Yadkori, D\u00e1vid P\u00e1l, and Csaba Szepesv\u00e1ri. 2011. Improved algorithms for linear stochastic bandits. Advances in neural information processing systems 24 (2011)."},{"key":"e_1_3_2_1_2_1","volume-title":"International Conference on Machine Learning. PMLR, 1638--1646","author":"Agarwal Alekh","year":"2014","unstructured":"Alekh Agarwal, Daniel Hsu, Satyen Kale, John Langford, Lihong Li, and Robert Schapire. 2014. Taming the monster: A fast and simple algorithm for contextual bandits. In International Conference on Machine Learning. PMLR, 1638--1646."},{"key":"e_1_3_2_1_3_1","volume-title":"International conference on machine learning. PMLR, 127--135","author":"Agrawal Shipra","year":"2013","unstructured":"Shipra Agrawal and Navin Goyal. 2013. Thompson sampling for contextual bandits with linear payoffs. In International conference on machine learning. PMLR, 127--135."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2792838.2800183"},{"key":"e_1_3_2_1_5_1","volume-title":"Finite-time analysis of the multiarmed bandit problem. Machine learning 47, 2","author":"Auer Peter","year":"2002","unstructured":"Peter Auer, Nicolo Cesa-Bianchi, and Paul Fischer. 2002. Finite-time analysis of the multiarmed bandit problem. Machine learning 47, 2 (2002), 235--256."},{"key":"e_1_3_2_1_6_1","volume-title":"Multiple randomization designs. arXiv preprint arXiv:2112.13495","author":"Bajari Patrick","year":"2021","unstructured":"Patrick Bajari, Brian Burdick, Guido W Imbens, Lorenzo Masoero, James McQueen, Thomas Richardson, and Ido M Rosen. 2021. Multiple randomization designs. arXiv preprint arXiv:2112.13495 (2021)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412217"},{"key":"e_1_3_2_1_8_1","volume-title":"An empirical evaluation of thompson sampling. Advances in neural information processing systems 24","author":"Chapelle Olivier","year":"2011","unstructured":"Olivier Chapelle and Lihong Li. 2011. An empirical evaluation of thompson sampling. Advances in neural information processing systems 24 (2011)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474601"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"e_1_3_2_1_11_1","volume-title":"Values of User Exploration in Recommender Systems. In Fifteenth ACM Conference on Recommender Systems. 85--95","author":"Chen Minmin","year":"2021","unstructured":"Minmin Chen, Yuyan Wang, Can Xu, Ya Le, Mohit Sharma, Lee Richardson, Su-Lin Wu, and Ed Chi. 2021. Values of User Exploration in Recommender Systems. In Fifteenth ACM Conference on Recommender Systems. 85--95."},{"key":"e_1_3_2_1_12_1","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 438--447","author":"Cheung Wang Chi","year":"2019","unstructured":"Wang Chi Cheung, Vincent Tan, and Zixin Zhong. 2019. A Thompson sampling algorithm for cascading bandits. In The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 438--447."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 208--214","author":"Chu Wei","year":"2011","unstructured":"Wei Chu, Lihong Li, Lev Reyzin, and Robert Schapire. 2011. Contextual bandits with linear payoff functions. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 208--214."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 1585--1593","author":"Ding Qin","year":"2021","unstructured":"Qin Ding, Cho-Jui Hsieh, and James Sharpnack. 2021. An efficient algorithm for generalized linear bandit: Online stochastic gradient descent and thompson sampling. In International Conference on Artificial Intelligence and Statistics. PMLR, 1585--1593."},{"key":"e_1_3_2_1_16_1","unstructured":"Audrey Durand Charis Achilleos Demetris Iacovides Katerina Strati Georgios D Mitsis and Joelle Pineau. 2018. Contextual bandits for adapting treatment in a mouse model of de novo carcinogenesis. In Machine learning for healthcare conference. PMLR 67--82."},{"key":"e_1_3_2_1_17_1","volume-title":"Parametric bandits: The generalized linear case. Advances in Neural Information Processing Systems 23","author":"Filippi Sarah","year":"2010","unstructured":"Sarah Filippi, Olivier Cappe, Aur\u00e9lien Garivier, and Csaba Szepesv\u00e1ri. 2010. Parametric bandits: The generalized linear case. Advances in Neural Information Processing Systems 23 (2010)."},{"key":"e_1_3_2_1_18_1","volume-title":"Filip De Turck, and Pieter Abbeel","author":"Houthooft Rein","year":"2016","unstructured":"Rein Houthooft, Xi Chen, Yan Duan, John Schulman, Filip De Turck, and Pieter Abbeel. 2016. Vime: Variational information maximizing exploration. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_1_19_1","volume-title":"Causal inference in statistics, social, and biomedical sciences","author":"Imbens Guido W","unstructured":"Guido W Imbens and Donald B Rubin. 2015. Causal inference in statistics, social, and biomedical sciences. Cambridge University Press."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401230"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474248"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314288"},{"key":"e_1_3_2_1_23_1","volume-title":"International Conference on Learning Representations.","author":"Joachims Thorsten","year":"2018","unstructured":"Thorsten Joachims, Adith Swaminathan, and Maarten De Rijke. 2018. Deep learning with logged bandit feedback. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_24_1","volume-title":"Trustworthy online controlled experiments: A practical guide to a\/b testing","author":"Kohavi Ron","unstructured":"Ron Kohavi, Diane Tang, and Ya Xu. 2020. Trustworthy online controlled experiments: A practical guide to a\/b testing. Cambridge University Press."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_1_26_1","volume-title":"Matrix inversion using Cholesky decomposition. In 2013 signal processing: Algorithms, architectures, arrangements, and applications (SPA)","author":"Krishnamoorthy Aravindh","unstructured":"Aravindh Krishnamoorthy and Deepak Menon. 2013. Matrix inversion using Cholesky decomposition. In 2013 signal processing: Algorithms, architectures, arrangements, and applications (SPA). IEEE, 70--72."},{"key":"e_1_3_2_1_27_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 6880--6892","author":"Kveton Branislav","year":"2022","unstructured":"Branislav Kveton, Ofer Meshi, Masrour Zoghi, and Zhen Qin. 2022. On the Value of Prior in Online Learning to Rank. In International Conference on Artificial Intelligence and Statistics. PMLR, 6880--6892."},{"key":"e_1_3_2_1_28_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR","author":"Kveton Branislav","year":"2020","unstructured":"Branislav Kveton, Manzil Zaheer, Csaba Szepesvari, Lihong Li, Mohammad Ghavamzadeh, and Craig Boutilier. 2020. Randomized exploration in generalized linear bandits. In International Conference on Artificial Intelligence and Statistics. PMLR, 2066--2076."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Tze Leung Lai Herbert Robbins et al. 1985. Asymptotically efficient adaptive allocation rules. Advances in applied mathematics 6 1 (1985) 4--22.","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"e_1_3_2_1_30_1","volume-title":"The epoch-greedy algorithm for multi-armed bandits with side information. Advances in neural information processing systems 20","author":"Langford John","year":"2007","unstructured":"John Langford and Tong Zhang. 2007. The epoch-greedy algorithm for multi-armed bandits with side information. Advances in neural information processing systems 20 (2007)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_1_32_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Li Lihong","year":"2017","unstructured":"Lihong Li, Yu Lu, and Dengyong Zhou. 2017. Provably optimal algorithms for generalized linear contextual bandits. In International Conference on Machine Learning. PMLR, 2071--2080."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12028"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240354"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2019.1918"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1287\/mksc.2018.1129"},{"key":"e_1_3_2_1_37_1","volume-title":"Mathematical proceedings of the Cambridge philosophical society","author":"Penrose Roger","unstructured":"Roger Penrose. 1955. A generalized inverse for matrices. In Mathematical proceedings of the Cambridge philosophical society, Vol. 51. Cambridge University Press, 406--413."},{"key":"e_1_3_2_1_38_1","volume-title":"Numerical recipes","author":"Press William H","unstructured":"William H Press, Saul A Teukolsky, William T Vetterling, and Brian P Flannery. 2007. Numerical recipes 3rd edition: The art of scientific computing. Cambridge university press.","edition":"3"},{"key":"e_1_3_2_1_39_1","volume-title":"Deep bayesian bandits showdown: An empirical comparison of bayesian deep networks for thompson sampling. arXiv preprint arXiv:1802.09127","author":"Riquelme Carlos","year":"2018","unstructured":"Carlos Riquelme, George Tucker, and Jasper Snoek. 2018. Deep bayesian bandits showdown: An empirical comparison of bayesian deep networks for thompson sampling. arXiv preprint arXiv:1802.09127 (2018)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372071"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159700"},{"key":"e_1_3_2_1_42_1","volume-title":"Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al.","author":"Silver David","year":"2016","unstructured":"David Silver, Aja Huang, Chris J Maddison, Arthur Guez, Laurent Sifre, George Van Den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al. 2016. Mastering the game of Go with deep neural networks and tree search. nature 529, 7587 (2016), 484--489."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498459"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/25.3-4.285"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3158369"},{"key":"e_1_3_2_1_46_1","volume-title":"Neural thompson sampling. arXiv preprint arXiv:2010.00827","author":"Zhang Weitong","year":"2020","unstructured":"Weitong Zhang, Dongruo Zhou, Lihong Li, and Quanquan Gu. 2020. Neural thompson sampling. arXiv preprint arXiv:2010.00827 (2020)."},{"key":"e_1_3_2_1_47_1","volume-title":"International Conference on Machine Learning. PMLR, 11492--11502","author":"Zhou Dongruo","year":"2020","unstructured":"Dongruo Zhou, Lihong Li, and Quanquan Gu. 2020. Neural contextual bandits with ucb-based exploration. In International Conference on Machine Learning. PMLR, 11492--11502."},{"key":"e_1_3_2_1_48_1","volume-title":"Zheng Wen, and Branislav Kveton.","author":"Zong Shi","year":"2016","unstructured":"Shi Zong, Hao Ni, Kenny Sung, Nan Rosemary Ke, Zheng Wen, and Branislav Kveton. 2016. Cascading bandits for large-scale recommendation problems. arXiv preprint arXiv:1603.05359 (2016). io"}],"event":{"name":"WSDM '24: The 17th ACM International Conference on Web Search and Data Mining","location":"Merida Mexico","acronym":"WSDM '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 17th ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616855.3635833","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3616855.3635833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:46:53Z","timestamp":1755823613000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616855.3635833"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,4]]},"references-count":48,"alternative-id":["10.1145\/3616855.3635833","10.1145\/3616855"],"URL":"https:\/\/doi.org\/10.1145\/3616855.3635833","relation":{},"subject":[],"published":{"date-parts":[[2024,3,4]]},"assertion":[{"value":"2024-03-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}