{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:00:23Z","timestamp":1775815223403,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,9,22]],"date-time":"2020-09-22T00:00:00Z","timestamp":1600732800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,9,22]]},"DOI":"10.1145\/3383313.3412252","type":"proceedings-article","created":{"date-parts":[[2020,9,19]],"date-time":"2020-09-19T02:28:22Z","timestamp":1600482502000},"page":"190-199","source":"Crossref","is-referenced-by-count":54,"title":["Keeping Dataset Biases out of the Simulation"],"prefix":"10.1145","author":[{"given":"Jin","family":"Huang","sequence":"first","affiliation":[{"name":"University of Amsterdam Amsterdam, The Netherlands"}]},{"given":"Harrie","family":"Oosterhuis","sequence":"additional","affiliation":[{"name":"University of Amsterdam Amsterdam, The Netherlands"}]},{"given":"Maarten","family":"de Rijke","sequence":"additional","affiliation":[{"name":"University of Amsterdam & Ahold Delhaize Amsterdam, The Netherlands"}]},{"given":"Herke","family":"van Hoof","sequence":"additional","affiliation":[{"name":"University of Amsterdam Amsterdam, The Netherlands"}]}],"member":"320","published-online":{"date-parts":[[2020,9,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/2566972.2566979"},{"key":"e_1_3_2_1_2_1","unstructured":"Greg Brockman Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016. OpenAI Gym. arXiv preprint arXiv:1606.01540(2016).  Greg Brockman Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016. OpenAI Gym. arXiv preprint arXiv:1606.01540(2016)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210014"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013312"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358131"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220122"},{"key":"e_1_3_2_1_8_1","volume-title":"Generative Adversarial User Model for Reinforcement Learning Based Recommendation System. In International Conference on Machine Learning. 1052\u20131061","author":"Chen Xinshi","year":"2019"},{"key":"e_1_3_2_1_9_1","unstructured":"Sungwoon Choi Heonseok Ha Uiwon Hwang Chanju Kim Jung-Woo Ha and Sungroh Yoon. 2018. Reinforcement Learning Based Recommender System Using Biclustering Technique. arXiv preprint arXiv:1801.05532(2018).  Sungwoon Choi Heonseok Ha Uiwon Hwang Chanju Kim Jung-Woo Ha and Sungroh Yoon. 2018. Reinforcement Learning Based Recommender System Using Biclustering Technique. arXiv preprint arXiv:1801.05532(2018)."},{"key":"e_1_3_2_1_10_1","unstructured":"Gabriel Dulac-Arnold Richard Evans Hado van Hasselt Peter Sunehag Timothy Lillicrap Jonathan Hunt Timothy Mann Theophane Weber Thomas Degris and Ben Coppin. 2015. Deep Reinforcement Learning in Large Discrete Action Spaces. arXiv preprint arXiv:1512.07679(2015).  Gabriel Dulac-Arnold Richard Evans Hado van Hasselt Peter Sunehag Timothy Lillicrap Jonathan Hunt Timothy Mann Theophane Weber Thomas Degris and Ben Coppin. 2015. Deep Reinforcement Learning in Large Discrete Action Spaces. arXiv preprint arXiv:1512.07679(2015)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159687"},{"key":"e_1_3_2_1_12_1","volume-title":"Probabilistic Matrix Factorization with Non-random Missing Data. In International Conference on Machine Learning. 1512\u20131520","author":"Hern\u00e1ndez-Lobato Jos\u00e9\u00a0Miguel","year":"2014"},{"key":"e_1_3_2_1_13_1","unstructured":"Eugene Ie Chih-wei Hsu Martin Mladenov Vihan Jain Sanmit Narvekar Jing Wang Rui Wu and Craig Boutilier. 2019. RecSim: A Configurable Simulation Platform for Recommender Systems. arXiv preprint arXiv:1909.04847(2019).  Eugene Ie Chih-wei Hsu Martin Mladenov Vihan Jain Sanmit Narvekar Jing Wang Rui Wu and Craig Boutilier. 2019. RecSim: A Configurable Simulation Platform for Recommender Systems. arXiv preprint arXiv:1909.04847(2019)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","volume-title":"Causal Inference in Statistics, Social, and Biomedical Sciences","author":"Imbens W","DOI":"10.1017\/CBO9781139025751"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018699"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684822.2685311"},{"key":"e_1_3_2_1_18_1","volume-title":"Statistical Analysis with Missing Data. Vol.\u00a0793","author":"Little JA"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1639714.1639717"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/3020488.3020521"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2365952.2365982"},{"key":"e_1_3_2_1_22_1","unstructured":"David Rohde Stephen Bonner Travis Dunlop Flavian Vasile and Alexandros Karatzoglou. 2018. RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising. arXiv preprint arXiv:1808.00720(2018).  David Rohde Stephen Bonner Travis Dunlop Flavian Vasile and Alexandros Karatzoglou. 2018. RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising. arXiv preprint arXiv:1808.00720(2018)."},{"key":"e_1_3_2_1_23_1","volume-title":"Observational Studies","author":"Rosenbaum R"},{"key":"e_1_3_2_1_24_1","volume-title":"International Conference on Machine Learning. 1670\u20131679","author":"Schnabel Tobias","year":"2016"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346981"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-017-0762-9"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1835804.1835895"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2043932.2043957"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2507157.2507160"},{"key":"e_1_3_2_1_31_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton S","year":"2018"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219961"},{"key":"e_1_3_2_1_33_1","volume-title":"International Conference on Machine Learning. 6638\u20136647","author":"Wang Xiaojie","year":"2019"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301435"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Shuo Zhang and Krisztian Balog. 2020. Evaluating Conversational Recommender Systems via User Simulation. arXiv preprint arXiv:2006.08732(2020).  Shuo Zhang and Krisztian Balog. 2020. Evaluating Conversational Recommender Systems via User Simulation. arXiv preprint arXiv:2006.08732(2020).","DOI":"10.1145\/3394486.3403202"},{"key":"e_1_3_2_1_36_1","unstructured":"Xiangyu Zhao Long Xia Zhuoye Ding Dawei Yin and Jiliang Tang. 2019. Toward Simulating Environments in Reinforcement Learning based Recommendations. arXiv preprint arXiv:1906.11462(2019).  Xiangyu Zhao Long Xia Zhuoye Ding Dawei Yin and Jiliang Tang. 2019. Toward Simulating Environments in Reinforcement Learning based Recommendations. arXiv preprint arXiv:1906.11462(2019)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_1_39_1","unstructured":"Xiangyu Zhao Liang Zhang Zhuoye Ding Dawei Yin Yihong Zhao and Jiliang Tang. 2017. Deep Reinforcement Learning for List-wise Recommendations. arXiv preprint arXiv:1801.00209(2017).  Xiangyu Zhao Liang Zhang Zhuoye Ding Dawei Yin Yihong Zhao and Jiliang Tang. 2017. Deep Reinforcement Learning for List-wise Recommendations. arXiv preprint arXiv:1801.00209(2017)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Xiangyu Zhao Xudong Zheng Xiwang Yang Xiaobing Liu and Jiliang Tang. 2020. Jointly Learning to Recommend and Advertise. arXiv preprint arXiv:2003.00097(2020).  Xiangyu Zhao Xudong Zheng Xiwang Yang Xiaobing Liu and Jiliang Tang. 2020. Jointly Learning to Recommend and Advertise. arXiv preprint arXiv:2003.00097(2020).","DOI":"10.1145\/3394486.3403384"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Lixin Zou Long Xia Zhuoye Ding Jiaxing Song Weidong Liu and Dawei Yin. 2019. Reinforcement Learning to Optimize Long-term User Engagement in Recommender Systems. arXiv preprint arXiv:1902.05570(2019).  Lixin Zou Long Xia Zhuoye Ding Jiaxing Song Weidong Liu and Dawei Yin. 2019. Reinforcement Learning to Optimize Long-term User Engagement in Recommender Systems. arXiv preprint arXiv:1902.05570(2019).","DOI":"10.1145\/3292500.3330668"}],"event":{"name":"RecSys '20: Fourteenth ACM Conference on Recommender Systems","location":"Virtual Event Brazil","acronym":"RecSys '20","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","SIGecom Special Interest Group on Economics and Computation"]},"container-title":["Fourteenth ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3383313.3412252","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3383313.3412252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:33:21Z","timestamp":1750199601000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3383313.3412252"}},"subtitle":["A Debiased Simulator for Reinforcement Learning based Recommender Systems"],"short-title":[],"issued":{"date-parts":[[2020,9,22]]},"references-count":42,"alternative-id":["10.1145\/3383313.3412252","10.1145\/3383313"],"URL":"https:\/\/doi.org\/10.1145\/3383313.3412252","relation":{},"subject":[],"published":{"date-parts":[[2020,9,22]]}}}