{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:17:35Z","timestamp":1783153055050,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792181","type":"proceedings-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T13:28:36Z","timestamp":1777296516000},"page":"5908-5919","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Off-Policy Learning with Limited Supply"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4790-5092","authenticated-orcid":false,"given":"Koichi","family":"Tanaka","sequence":"first","affiliation":[{"name":"Keio University, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7443-5325","authenticated-orcid":false,"given":"Ren","family":"Kishimoto","sequence":"additional","affiliation":[{"name":"Institute of Science Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6472-4969","authenticated-orcid":false,"given":"Bushun","family":"Kawagishi","sequence":"additional","affiliation":[{"name":"Meiji University, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0314-3384","authenticated-orcid":false,"given":"Yusuke","family":"Narita","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9257-9063","authenticated-orcid":false,"given":"Yasuo","family":"Yamamoto","sequence":"additional","affiliation":[{"name":"LY Corporation, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6767-3662","authenticated-orcid":false,"given":"Nobuyuki","family":"Shimizu","sequence":"additional","affiliation":[{"name":"LY Corporation, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4357-5835","authenticated-orcid":false,"given":"Yuta","family":"Saito","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, NY, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Linear contextual bandits with knapsacks. Advances in neural information processing systems","author":"Agrawal Shipra","year":"2016","unstructured":"Shipra Agrawal and Nikhil Devanur. 2016. Linear contextual bandits with knapsacks. Advances in neural information processing systems, Vol. 29 (2016)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3164539"},{"key":"e_1_3_2_1_3_1","volume-title":"Conference on Learning Theory. PMLR, 1109-1134","author":"Badanidiyuru Ashwinkumar","year":"2014","unstructured":"Ashwinkumar Badanidiyuru, John Langford, and Aleksandrs Slivkins. 2014. Resourceful contextual bandits. In Conference on Learning Theory. PMLR, 1109-1134."},{"key":"e_1_3_2_1_4_1","article-title":"Counterfactual Reasoning and Learning Systems: The Example of Computational Advertising","volume":"14","author":"Bottou L\u00e9on","year":"2013","unstructured":"L\u00e9on Bottou, Jonas Peters, Joaquin Qui nonero-Candela, Denis X Charles, D Max Chickering, Elon Portugaly, Dipankar Ray, Patrice Simard, and Ed Snelson. 2013. Counterfactual Reasoning and Learning Systems: The Example of Computational Advertising. Journal of Machine Learning Research, Vol. 14, 11 (2013).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3133034"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1214\/14-STS500"},{"key":"e_1_3_2_1_7_1","first-page":"1447","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Farajtabar Mehrdad","year":"2018","unstructured":"Mehrdad Farajtabar, Yinlam Chow, and Mohammad Ghavamzadeh. 2018. More Robust Doubly Robust Off-Policy Evaluation. In Proceedings of the 35th International Conference on Machine Learning, Vol. 80. PMLR, 1447-1456."},{"key":"e_1_3_2_1_8_1","volume-title":"Marcello Restelli, and Paolo Cremonesi.","author":"Felicioni Nicolo","year":"2022","unstructured":"Nicolo Felicioni, Maurizio Ferrari Dacrema, Marcello Restelli, and Paolo Cremonesi. 2022. Off-Policy Evaluation with Deficient Support Using Side Information. Advances in Neural Information Processing Systems, Vol. 35 (2022)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557220"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159687"},{"key":"e_1_3_2_1_11_1","first-page":"5247","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Kallus Nathan","year":"2021","unstructured":"Nathan Kallus, Yuta Saito, and Masatoshi Uehara. 2021. Optimal Off-Policy Evaluation from Multiple Logging Policies. In Proceedings of the 38th International Conference on Machine Learning, Vol. 139. PMLR, 5247-5256."},{"key":"e_1_3_2_1_12_1","volume-title":"Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation. In International Conference on Learning Representations.","author":"Kiyohara Haruka","year":"2024","unstructured":"Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, and Yuta Saito. 2024a. Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645343"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498380"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599447"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2740908.2742562"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems. 5361-5371","author":"Liu Qiang","year":"2018","unstructured":"Qiang Liu, Lihong Li, Ziyang Tang, and Dengyong Zhou. 2018. Breaking the curse of horizon: infinite-horizon off-policy estimation. In Proceedings of the 32nd International Conference on Neural Information Processing Systems. 5361-5371."},{"key":"e_1_3_2_1_18_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Metelli Alberto Maria","year":"2021","unstructured":"Alberto Maria Metelli, Alessio Russo, and Marcello Restelli. 2021. Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and Learning. Advances in Neural Information Processing Systems, Vol. 34 (2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645446"},{"key":"e_1_3_2_1_21_1","volume-title":"Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track.","author":"Saito Yuta","year":"2021","unstructured":"Yuta Saito, Shunsuke Aihara, Megumi Matsutani, and Yusuke Narita. 2021a. Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3473320"},{"key":"e_1_3_2_1_23_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Saito Yuta","year":"2022","unstructured":"Yuta Saito and Thorsten Joachims. 2022. Off-Policy Evaluation for Large Action Spaces via Embeddings. In International Conference on Machine Learning. PMLR, 19089-19122."},{"key":"e_1_3_2_1_24_1","volume-title":"Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling. arXiv preprint arXiv:2305.08062","author":"Saito Yuta","year":"2023","unstructured":"Yuta Saito, Qingyang Ren, and Thorsten Joachims. 2023. Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling. arXiv preprint arXiv:2305.08062 (2023)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474245"},{"key":"e_1_3_2_1_26_1","volume-title":"POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition. arXiv preprint arXiv:2402.06151","author":"Saito Yuta","year":"2024","unstructured":"Yuta Saito, Jihan Yao, and Thorsten Joachims. 2024b. POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition. arXiv preprint arXiv:2402.06151 (2024)."},{"key":"e_1_3_2_1_27_1","first-page":"9167","volume-title":"Proceedings of the 37th International Conference on Machine Learning","volume":"119","author":"Su Yi","year":"2020","unstructured":"Yi Su, Maria Dimakopoulou, Akshay Krishnamurthy, and Miroslav Dud\u00edk. 2020. Doubly Robust Off-Policy Evaluation with Shrinkage. In Proceedings of the 37th International Conference on Machine Learning, Vol. 119. PMLR, 9167-9176."},{"key":"e_1_3_2_1_28_1","first-page":"6005","volume-title":"International Conference on Machine Learning","volume":"84","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, Vol. 84. 6005-6014."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2886805"},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on Machine Learning. PMLR, 814-823","author":"Swaminathan Adith","year":"2015","unstructured":"Adith Swaminathan and Thorsten Joachims. 2015b. Counterfactual risk minimization: Learning from logged bandit feedback. In International Conference on Machine Learning. PMLR, 814-823."},{"key":"e_1_3_2_1_31_1","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Swaminathan Adith","year":"2015","unstructured":"Adith Swaminathan and Thorsten Joachims. 2015c. The Self-Normalized Estimator for Counterfactual Learning. Advances in Neural Information Processing Systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_32_1","first-page":"3632","article-title":"Off-Policy Evaluation for Slate Recommendation","volume":"30","author":"Swaminathan Adith","year":"2017","unstructured":"Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal, Miro Dudik, John Langford, Damien Jose, and Imed Zitouni. 2017. Off-Policy Evaluation for Slate Recommendation. In Advances in Neural Information Processing Systems, Vol. 30. 3632-3642.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_33_1","volume-title":"A review of off-policy evaluation in reinforcement learning. arXiv preprint arXiv:2212.06355","author":"Uehara Masatoshi","year":"2022","unstructured":"Masatoshi Uehara, Chengchun Shi, and Nathan Kallus. 2022. A review of off-policy evaluation in reinforcement learning. arXiv preprint arXiv:2212.06355 (2022)."},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Machine Learning. PMLR, 3589-3597","author":"Wang Yu-Xiang","year":"2017","unstructured":"Yu-Xiang Wang, Alekh Agarwal, and Miroslav Dudik. 2017. Optimal and adaptive off-policy evaluation in contextual bandits. In International Conference on Machine Learning. PMLR, 3589-3597."},{"key":"e_1_3_2_1_35_1","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Wu Huasen","year":"2015","unstructured":"Huasen Wu, Rayadurgam Srikant, Xin Liu, and Chong Jiang. 2015. Algorithms with logarithmic or sublinear regret for constrained contextual bandits. Advances in Neural Information Processing Systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107558"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2788565"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:37:13Z","timestamp":1783150633000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792181"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":37,"alternative-id":["10.1145\/3774904.3792181","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792181","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}