{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T18:54:38Z","timestamp":1770663278640,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,8]],"date-time":"2023-08-08T00:00:00Z","timestamp":1691452800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,8]]},"DOI":"10.1145\/3600211.3604669","type":"proceedings-article","created":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T18:41:37Z","timestamp":1693334497000},"page":"58-69","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["User Tampering in Reinforcement Learning Recommender Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5967-3782","authenticated-orcid":false,"given":"Atoosa","family":"Kasirzadeh","sequence":"first","affiliation":[{"name":"University of Edinburgh, United Kingdom and Australian National University, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5588-9052","authenticated-orcid":false,"given":"Charles","family":"Evans","sequence":"additional","affiliation":[{"name":"Australian National University, Australia"}]}],"member":"320","published-online":{"date-parts":[[2023,8,29]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11257-019-09256-1"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543846"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2810062"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/221"},{"key":"e_1_3_2_1_5_1","volume-title":"Breaking the Social Media Prism: How to Make our Platforms Less Polarizing","author":"Bail A.","unstructured":"Christopher\u00a0A. Bail. 2021. Breaking the Social Media Prism: How to Make our Platforms Less Polarizing. Princeton University Press, Princeton, New Jersey."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1804840115"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2013.03.012"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3478849"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17368"},{"key":"e_1_3_2_1_10_1","volume-title":"Reward tampering problems and solutions in reinforcement learning: A causal influence diagram perspective. Synthese","author":"Everitt Tom","year":"2021","unstructured":"Tom Everitt, Marcus Hutter, Ramana Kumar, and Victoria Krakovna. 2021. Reward tampering problems and solutions in reinforcement learning: A causal influence diagram perspective. Synthese (2021), 1\u201333."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i9.21186"},{"key":"e_1_3_2_1_12_1","volume-title":"Personalized News Recommendation Based on Collaborative Filtering. In 2012 IEEE\/WIC\/ACM International Conferences on Web Intelligence and Intelligent Agent Technology, Vol.\u00a01. 437\u2013441","author":"Garcin Florent","year":"2012","unstructured":"Florent Garcin, Kai Zhou, Boi Faltings, and Vincent Schickel. 2012. Personalized News Recommendation Based on Collaborative Filtering. In 2012 IEEE\/WIC\/ACM International Conferences on Web Intelligence and Intelligent Agent Technology, Vol.\u00a01. 437\u2013441."},{"key":"e_1_3_2_1_13_1","volume-title":"Horizon: Facebook\u2019s Open Source Applied Reinforcement Learning Platform. Facebook AI","author":"Gauci Jason","year":"2018","unstructured":"Jason Gauci, Edoardo Conti, Yitao Liang, Kittipat Virochsiri, Yuchen He, Zachary Kaden, Vivek Narayanan, and Xiaohui Ye. 2018. Horizon: Facebook\u2019s Open Source Applied Reinforcement Learning Platform. Facebook AI (2018)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622620.1622634"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314288"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347020"},{"key":"e_1_3_2_1_17_1","volume-title":"Hidden Incentives for Auto-Induced Distributional Shift. ArXiv arXiv:2009.09153","author":"Krueger David","year":"2020","unstructured":"David Krueger, Tegan Maharaj, and Jan Leike. 2020. Hidden Incentives for Auto-Induced Distributional Shift. ArXiv arXiv:2009.09153 (2020)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_1_19_1","volume-title":"Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling. ArXiv arXiv:1810.12027","author":"Liu Feng","year":"2018","unstructured":"Feng Liu, Ruiming Tang, Xutao Li, Yunming Ye, Haokun Chen, Huifeng Guo, and Yuzhou Zhang. 2018. Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling. ArXiv arXiv:1810.12027 (2018)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1719970.1719976"},{"key":"e_1_3_2_1_21_1","volume-title":"Reinforcement Learning-based Product Delivery Frequency Control. Facebook AI","author":"Liu Yang","year":"2020","unstructured":"Yang Liu, Zhengxing Chen, Kittipat Virochsiri, Juan Wang, Jiahao Wu, and Feng Liang. 2020. Reinforcement Learning-based Product Delivery Frequency Control. Facebook AI (2020)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/2887007.2887038"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-020-00950-y"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380196"},{"key":"e_1_3_2_1_25_1","volume-title":"Markov decision processes. Handbooks in operations research and management science 2","author":"Puterman L","year":"1990","unstructured":"Martin\u00a0L Puterman. 1990. Markov decision processes. Handbooks in operations research and management science 2 (1990), 331\u2013434."},{"key":"e_1_3_2_1_26_1","volume-title":"Filter Bubbles and the Future of Artificial Intelligence. https:\/\/www.youtube.com\/watch?v=ZkV7anCPfaY&t=230s&ab_channel=LongNowFoundation. Accessed","author":"Russell J.","year":"2021","unstructured":"Stuart\u00a0J. Russell. 2019. Filter Bubbles and the Future of Artificial Intelligence. https:\/\/www.youtube.com\/watch?v=ZkV7anCPfaY&t=230s&ab_channel=LongNowFoundation. Accessed June 2, 2021."},{"key":"e_1_3_2_1_27_1","volume-title":"Human Compatible: AI and the Problem of Control. Allen Lane","author":"Russell J.","year":"2019","unstructured":"Stuart\u00a0J. Russell. 2019. Human Compatible: AI and the Problem of Control. Allen Lane, London."},{"key":"e_1_3_2_1_28_1","volume-title":"Toward Social Media Content Recommendation Integrated with Data Science and Machine Learning Approach for E-Learners. Symmetry 12, 11","author":"Shahbazi Zeinab","year":"2020","unstructured":"Zeinab Shahbazi and Yung\u00a0Cheol Byun. 2020. Toward Social Media Content Recommendation Integrated with Data Science and Machine Learning Approach for E-Learners. Symmetry 12, 11 (2020)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/1046920.1088715"},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on Machine Learning Workshop.","author":"Stray Jonathan","year":"2020","unstructured":"Jonathan Stray, Steven Adler, and Dylan Hadfield-Menell. 2020. What are you optimizing for? Aligning Recommender Systems with Human Values. In Participatory Approaches to Machine Learning. International Conference on Machine Learning Workshop."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1363686.1363954"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1297231.1297250"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2645710.2645732"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767707"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939878"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"}],"event":{"name":"AIES '23: AAAI\/ACM Conference on AI, Ethics, and Society","location":"Montr\u00e9al QC Canada","acronym":"AIES '23","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence"]},"container-title":["Proceedings of the 2023 AAAI\/ACM Conference on AI, Ethics, and Society"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3600211.3604669","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3600211.3604669","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:39Z","timestamp":1750178259000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3600211.3604669"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,8]]},"references-count":38,"alternative-id":["10.1145\/3600211.3604669","10.1145\/3600211"],"URL":"https:\/\/doi.org\/10.1145\/3600211.3604669","relation":{},"subject":[],"published":{"date-parts":[[2023,8,8]]},"assertion":[{"value":"2023-08-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}