{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:03:42Z","timestamp":1750309422945,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":8,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T00:00:00Z","timestamp":1728345600000},"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":[[2024,10,8]]},"DOI":"10.1145\/3640457.3688058","type":"proceedings-article","created":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T15:39:28Z","timestamp":1728401968000},"page":"803-805","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Off-Policy Selection for Optimizing Ad Display Timing in Mobile Games (Samsung Instant Plays)"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7056-9808","authenticated-orcid":false,"given":"Katarzyna","family":"Siudek-Tkaczuk","sequence":"first","affiliation":[{"name":"Samsung R&D Institute Poland, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3480-7294","authenticated-orcid":false,"given":"S\u0142awomir","family":"Kapka","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute Poland, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5899-5997","authenticated-orcid":false,"given":"J\u0119drzej","family":"Alchimowicz","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute Poland, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4303-0532","authenticated-orcid":false,"given":"Bart\u0142omiej","family":"Swoboda","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute Poland, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5370-6598","authenticated-orcid":false,"given":"Micha\u0142","family":"Romaniuk","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute Poland, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Horizon: Facebook\u2019s Open Source Applied Reinforcement Learning Platform. arXiv preprint arXiv:1811.00260","author":"Gauci Jason","year":"2018","unstructured":"Jason Gauci, Edoardo Conti, Yitao Liang, Kittipat Virochsiri, Zhengxing Chen, Yuchen He, Zachary Kaden, Vivek Narayanan, and Xiaohui Ye. 2018. Horizon: Facebook\u2019s Open Source Applied Reinforcement Learning Platform. arXiv preprint arXiv:1811.00260 (2018)."},{"key":"e_1_3_2_1_2_1","unstructured":"Josiah\u00a0P. Hanna Scott Niekum and Peter Stone. 2019. Importance Sampling Policy Evaluation with an Estimated Behavior Policy. arxiv:1806.01347\u00a0[cs.LG]"},{"key":"e_1_3_2_1_3_1","volume-title":"Doubly Robust Off-policy Evaluation for Reinforcement Learning. CoRR abs\/1511.03722","author":"Jiang Nan","year":"2015","unstructured":"Nan Jiang and Lihong Li. 2015. Doubly Robust Off-policy Evaluation for Reinforcement Learning. CoRR abs\/1511.03722 (2015). arXiv:1511.03722http:\/\/arxiv.org\/abs\/1511.03722"},{"key":"e_1_3_2_1_4_1","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra and Martin Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. arxiv:1312.5602\u00a0[cs.LG]"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 13th USENIX conference on Operating Systems Design and Implementation. 561\u2013577","author":"Moritz Philipp","year":"2018","unstructured":"Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael\u00a0I Jordan, 2018. Ray: a distributed framework for emerging AI applications. In Proceedings of the 13th USENIX conference on Operating Systems Design and Implementation. 561\u2013577."},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Machine Learning. PMLR, 34556\u201334583","author":"Uchendu Ikechukwu","year":"2023","unstructured":"Ikechukwu Uchendu, Ted Xiao, Yao Lu, Banghua Zhu, Mengyuan Yan, Jos\u00e9phine Simon, Matthew Bennice, Chuyuan Fu, Cong Ma, Jiantao Jiao, 2023. Jump-start reinforcement learning. In International Conference on Machine Learning. PMLR, 34556\u201334583."},{"key":"e_1_3_2_1_7_1","volume-title":"Han Liu, and Tong Zhang.","author":"Wang Qing","year":"2018","unstructured":"Qing Wang, Jiechao Xiong, Lei Han, peng sun, Han Liu, and Tong Zhang. 2018. Exponentially Weighted Imitation Learning for Batched Historical Data. In Advances in Neural Information Processing Systems, S.\u00a0Bengio, H.\u00a0Wallach, H.\u00a0Larochelle, K.\u00a0Grauman, N.\u00a0Cesa-Bianchi, and R.\u00a0Garnett (Eds.). Vol.\u00a031. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2018\/file\/4aec1b3435c52abbdf8334ea0e7141e0-Paper.pdf"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/502"}],"event":{"name":"RecSys '24: 18th ACM Conference on Recommender Systems","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval","SIGCHI ACM Special Interest Group on Computer-Human Interaction"],"location":"Bari Italy","acronym":"RecSys '24"},"container-title":["18th ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640457.3688058","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3640457.3688058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:29Z","timestamp":1750294709000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640457.3688058"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,8]]},"references-count":8,"alternative-id":["10.1145\/3640457.3688058","10.1145\/3640457"],"URL":"https:\/\/doi.org\/10.1145\/3640457.3688058","relation":{},"subject":[],"published":{"date-parts":[[2024,10,8]]},"assertion":[{"value":"2024-10-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}