{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:08:49Z","timestamp":1757617729162,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,22]]},"DOI":"10.1145\/3705328.3748114","type":"proceedings-article","created":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T10:46:13Z","timestamp":1757155573000},"page":"949-953","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Off-Policy Evaluation of Content Blending in Station-Based Music Experiences"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3128-7465","authenticated-orcid":false,"given":"Chelsea","family":"Weaver","sequence":"first","affiliation":[{"name":"Amazon Music, Seattle, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2358-3079","authenticated-orcid":false,"given":"Arvind","family":"Balasubramanian","sequence":"additional","affiliation":[{"name":"Amazon Music, Seattle, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3363-0186","authenticated-orcid":false,"given":"Juan","family":"Borgnino","sequence":"additional","affiliation":[{"name":"Amazon Music, Culver City, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9515-5456","authenticated-orcid":false,"given":"Ben","family":"London","sequence":"additional","affiliation":[{"name":"Amazon Music, Seattle, WA, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,9,7]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"crossref","unstructured":"Aman Agarwal Soumya Basu Tobias Schnabel and Thorsten Joachims. 2017. Effective Evaluation Using Logged Bandit Feedback from Multiple Loggers. Knowledge Discovery and Data Mining (2017).","DOI":"10.1145\/3097983.3098155"},{"key":"e_1_3_3_3_3_2","volume-title":"International Conference on Machine Learning","author":"Dudik Miroslav","year":"2011","unstructured":"Miroslav Dudik, John Langford, and Lihong Li. 2011. Doubly Robust Policy Evaluation and Learning. In International Conference on Machine Learning."},{"key":"e_1_3_3_3_4_2","volume-title":"International Conference on Machine Learning","author":"Farajtabar Mehrdad","year":"2018","unstructured":"Mehrdad Farajtabar, Yinlam Chow, and Mohammad Ghavamzadeh. 2018. More Robust Doubly Robust Off-policy Evaluation. In International Conference on Machine Learning."},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159687"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"crossref","unstructured":"Daniel\u00a0G Horvitz and Donovan\u00a0J Thompson. 1952. A generalization of sampling without replacement from a finite universe. J. Amer. Statist. Assoc. 47 260 (1952) 663\u2013685.","DOI":"10.1080\/01621459.1952.10483446"},{"key":"e_1_3_3_3_7_2","volume-title":"International Conference on Machine Learning","author":"Jiang Nan","year":"2016","unstructured":"Nan Jiang and Lihong Li. 2016. Doubly Robust Off-policy Value Evaluation for Reinforcement Learning. In International Conference on Machine Learning."},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018699"},{"key":"e_1_3_3_3_9_2","volume-title":"Neural Information Processing Systems","author":"Kallus Nathan","year":"2018","unstructured":"Nathan Kallus. 2018. Balanced Policy Evaluation and Learning. In Neural Information Processing Systems."},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390223"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19460-3"},{"key":"e_1_3_3_3_12_2","volume-title":"Artificial Intelligence and Statistics","author":"Li Lihong","year":"2015","unstructured":"Lihong Li, Remi Munos, and Csaba Szepesv\u00e1ri. 2015. Toward Minimax Off-policy Value Estimation. In Artificial Intelligence and Statistics."},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688059"},{"key":"e_1_3_3_3_14_2","unstructured":"Anqi Liu Hao Liu Anima Anandkumar and Yisong Yue. 2019. Triply Robust Off-Policy Evaluation. CoRR abs\/1911.05811 (2019)."},{"key":"e_1_3_3_3_15_2","volume-title":"CONSEQUENCES+REVEAL Workshop \u2013 RecSys","author":"London Ben","year":"2022","unstructured":"Ben London and Thorsten Joachims. 2022. Control Variate Diagnostics for Detecting Problems in Logged Bandit Feedback. In CONSEQUENCES+REVEAL Workshop \u2013 RecSys."},{"key":"e_1_3_3_3_16_2","volume-title":"Neural Information Processing Systems","author":"Mahmood A.\u00a0Rupam","year":"2014","unstructured":"A.\u00a0Rupam Mahmood, Hado van Hasselt, and Richard Sutton. 2014. Weighted importance sampling for off-policy learning with linear function approximation. In Neural Information Processing Systems."},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481893"},{"key":"e_1_3_3_3_18_2","volume-title":"International Conference on Machine Learning","author":"Schnabel Tobias","year":"2016","unstructured":"Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak, and Thorsten Joachims. 2016. Recommendations as Treatments: Debiasing Learning and Evaluation. In International Conference on Machine Learning."},{"key":"e_1_3_3_3_19_2","volume-title":"Neural Information Processing Systems","author":"Strehl Alex","year":"2010","unstructured":"Alex Strehl, John Langford, Lihong Li, and Sham Kakade. 2010. Learning from Logged Implicit Exploration Data. In Neural Information Processing Systems."},{"key":"e_1_3_3_3_20_2","volume-title":"International Conference on Machine Learning","author":"Su Yi","year":"2019","unstructured":"Yi Su, Lequn Wang, Michele Santacatterina, and Thorsten Joachims. 2019. CAB: Continuous Adaptive Blending for Policy Evaluation and Learning. In International Conference on Machine Learning."},{"key":"e_1_3_3_3_21_2","volume-title":"Neural Information Processing Systems","author":"Swaminathan Adith","year":"2015","unstructured":"Adith Swaminathan and Thorsten Joachims. 2015. The Self-Normalized Estimator for Counterfactual Learning. In Neural Information Processing Systems."},{"key":"e_1_3_3_3_22_2","volume-title":"International Conference on Machine Learning","author":"Thomas Phillip","year":"2016","unstructured":"Phillip Thomas and Emma Brunskill. 2016. Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning. In International Conference on Machine Learning."},{"key":"e_1_3_3_3_23_2","volume-title":"International Conference on Machine Learning","author":"Vlassis Nikos","year":"2019","unstructured":"Nikos Vlassis, Aurelien Bibaut, Maria Dimakopoulou, and Tony Jebara. 2019. On the Design of Estimators for Bandit Off-Policy Evaluation. In International Conference on Machine Learning."},{"key":"e_1_3_3_3_24_2","volume-title":"International Conference on Machine Learning","author":"Wang Yu-Xiang.","year":"2017","unstructured":"Yu-Xiang. Wang, Alekh Agarwal, and Miroslav Dud\u00edk. 2017. Optimal and Adaptive Off-policy Evaluation in Contextual Bandits. In International Conference on Machine Learning."}],"event":{"name":"RecSys '25: Nineteenth ACM Conference on Recommender Systems","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGIR ACM Special Interest Group on Information Retrieval","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Prague Czech Republic","acronym":"RecSys '25"},"container-title":["Proceedings of the Nineteenth ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3705328.3748114","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T11:40:54Z","timestamp":1757158854000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3705328.3748114"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,7]]},"references-count":23,"alternative-id":["10.1145\/3705328.3748114","10.1145\/3705328"],"URL":"https:\/\/doi.org\/10.1145\/3705328.3748114","relation":{},"subject":[],"published":{"date-parts":[[2025,9,7]]},"assertion":[{"value":"2025-09-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}