{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T20:54:46Z","timestamp":1767819286818,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":28,"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"}],"funder":[{"DOI":"10.13039\/501100006374","name":"University of Washington","doi-asserted-by":"publisher","award":["Carwein-Andrews Graduate Fellowship"],"award-info":[{"award-number":["Carwein-Andrews Graduate Fellowship"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,8]]},"DOI":"10.1145\/3640457.3688021","type":"proceedings-article","created":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T11:39:28Z","timestamp":1728387568000},"page":"1355-1357","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Personalized Health Recommendations via Offline Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5828-0937","authenticated-orcid":false,"given":"Larry Donald","family":"Preuett","sequence":"first","affiliation":[{"name":"Center for Data Science, University of Washington, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543846"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-022513-115553"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1049\/ic.2010.0287"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582900.3582905"},{"key":"e_1_3_2_1_5_1","volume-title":"Addressing Function Approximation Error in Actor-Critic Methods. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:3544558","author":"Fujimoto Scott","year":"2018","unstructured":"Scott Fujimoto, Herke van Hoof, and David Meger. 2018. Addressing Function Approximation Error in Actor-Critic Methods. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:3544558"},{"key":"e_1_3_2_1_6_1","unstructured":"Matthew Hausknecht and Peter Stone. 2015. Deep Recurrent Q-Learning for Partially Observable MDPs. https:\/\/arxiv.org\/abs\/1507.06527. Accessed: 2024-6-16."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/2981562.2981649"},{"key":"e_1_3_2_1_8_1","volume-title":"Advances in Neural Information Processing Systems, M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.S. Liang, and J.\u00a0Wortman Vaughan (Eds.). Vol.\u00a034. Curran Associates","author":"Janner Michael","year":"2021","unstructured":"Michael Janner, Qiyang Li, and Sergey Levine. 2021. Offline Reinforcement Learning as One Big Sequence Modeling Problem. In Advances in Neural Information Processing Systems, M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.S. Liang, and J.\u00a0Wortman Vaughan (Eds.). Vol.\u00a034. Curran Associates, Inc., 1273\u20131286. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/099fe6b0b444c23836c4a5d07346082b-Paper.pdf"},{"key":"e_1_3_2_1_9_1","unstructured":"Cheryl Nott Nicholas Mark Sunil Shinde Ankur\u00a0Teredesai Jodi\u00a0Chiam Aloysius\u00a0Lim. 2024. Co-Pilot for Health: Personalized Algorithmic AI Nudging to Improve Health Outcomes. https:\/\/arxiv.org\/abs\/2401.10816. Accessed: 2024-6-17."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0213-5"},{"key":"e_1_3_2_1_11_1","volume-title":"Neural Information Processing Systems Workshop on Machine Learning for Health. 1.","author":"Komorowski Matthieu","year":"2016","unstructured":"Matthieu Komorowski, A Gordon, LA Celi, and A Faisal. 2016. A Markov Decision Process to suggest optimal treatment of severe infections in intensive care. In Neural Information Processing Systems Workshop on Machine Learning for Health. 1."},{"key":"e_1_3_2_1_12_1","volume-title":"Offline Reinforcement Learning with Implicit Q-Learning. In The Tenth International Conference on Learning Representations, ICLR 2022","author":"Kostrikov Ilya","year":"2022","unstructured":"Ilya Kostrikov, Ashvin Nair, and Sergey Levine. 2022. Offline Reinforcement Learning with Implicit Q-Learning. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=68n2s9ZJWF8"},{"key":"e_1_3_2_1_13_1","volume-title":"International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:84842462","author":"Le Hoang\u00a0Minh","year":"2019","unstructured":"Hoang\u00a0Minh Le, Cameron Voloshin, and Yisong Yue. 2019. Batch Policy Learning under Constraints. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:84842462"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3280161"},{"key":"e_1_3_2_1_16_1","volume-title":"AAAI Workshop - Technical Report WS-14-08","author":"Marivate V.","year":"2014","unstructured":"V. Marivate, J. Chemali, E. Brunskill, and M. Littmanf. 2014. Quantifying uncertainty in batch personalized sequential decision making. AAAI Workshop - Technical Report WS-14-08 (2014), 26\u201330."},{"key":"e_1_3_2_1_17_1","volume-title":"Playing Atari with Deep Reinforcement Learning","author":"Mnih Volodymyr","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin\u00a0A. Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. http:\/\/arxiv.org\/abs\/1312.5602. Accessed: 2023-11-08."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1198\/016214501753382327"},{"key":"e_1_3_2_1_19_1","volume-title":"Ensuring quality cancer care through the oncology workforce","author":"National Cancer Policy Forum and Institute of Medicine. 2009.","unstructured":"National Cancer Policy Forum and Institute of Medicine. 2009. Ensuring quality cancer care through the oncology workforce. National Academies Press, Washington, D.C., DC."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3234150"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","unstructured":"Aniruddh Raghu Matthieu Komorowski Leo\u00a0Anthony Celi Peter Szolovits and Marzyeh Ghassemi. 2017. Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning Approach. https:\/\/doi.org\/10.48550\/arXiv.1705.08422 arXiv:1705.08422 [cs].","DOI":"10.48550\/arXiv.1705.08422"},{"key":"e_1_3_2_1_23_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. https:\/\/arxiv.org\/abs\/1707.06347. Accessed: 2023-11-08."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning -","volume":"48","author":"S.","unstructured":"Philip\u00a0S. Thomas and Emma Brunskill. 2016. Data-Efficient off-Policy Policy Evaluation for Reinforcement Learning. In Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48 (New York, NY, USA) (ICML\u201916). JMLR.org, 2139\u20132148."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021","author":"Voloshin Cameron","year":"2021","unstructured":"Cameron Voloshin, Hoang\u00a0Minh Le, Nan Jiang, and Yisong Yue. 2021. Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December 2021, virtual, Joaquin Vanschoren and Sai-Kit Yeung (Eds.). https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper\/2021\/hash\/a5e00132373a7031000fd987a3c9f87b-Abstract-round1.html"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000000520"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401134"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","unstructured":"Xin Xin Alexandros Karatzoglou Ioannis Arapakis and Joemon\u00a0M. Jose. 2020. Self-Supervised Reinforcement Learning for Recommender Systems. https:\/\/doi.org\/10.48550\/arXiv.2006.05779 arXiv:2006.05779 [cs].","DOI":"10.48550\/arXiv.2006.05779"}],"event":{"name":"RecSys '24: 18th ACM Conference on Recommender Systems","location":"Bari Italy","acronym":"RecSys '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["18th ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640457.3688021","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3640457.3688021","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T19:48:50Z","timestamp":1767815330000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640457.3688021"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,8]]},"references-count":28,"alternative-id":["10.1145\/3640457.3688021","10.1145\/3640457"],"URL":"https:\/\/doi.org\/10.1145\/3640457.3688021","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"}}]}}