{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T23:00:22Z","timestamp":1783465222297,"version":"3.55.0"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T00:00:00Z","timestamp":1717545600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Hybrid Intelligence Center"},{"name":"Dutch Ministry of Education, Culture and Science"},{"DOI":"10.13039\/501100003246","name":"Netherlands Organisation for Scientific Research","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"crossref"}]},{"name":"LESSEN","award":["NWA.1389.20.183"],"award-info":[{"award-number":["NWA.1389.20.183"]}]},{"DOI":"10.13039\/501100003246","name":"Dutch Research Council","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"crossref"}]},{"name":"FINDHR"},{"name":"European Union\u2019s Horizon Europe research and innovation program","award":["101070212"],"award-info":[{"award-number":["101070212"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Recomm. Syst."],"published-print":{"date-parts":[[2024,9,30]]},"abstract":"<jats:p>Simulators can provide valuable insights for researchers and practitioners who wish to improve recommender systems, because they allow one to easily tweak the experimental setup in which recommender systems operate, and as a result lower the cost of identifying general trends and uncovering novel findings about the candidate methods. A key requirement to enable this accelerated improvement cycle is that the simulator is able to span the various sources of complexity that can be found in the real recommendation environment that it simulates.<\/jats:p>\n          <jats:p>With the emergence of interactive and data-driven methods\u2014e.g., reinforcement learning or online and counterfactual learning-to-rank\u2014that aim to achieve user-related goals beyond the traditional accuracy-centric objectives, adequate simulators are needed. In particular, such simulators must model the various mechanisms that render the recommendation environment dynamic and interactive, e.g., the effect of recommendations on the user or the effect of biased data on subsequent iterations of the recommender system. We therefore propose SARDINE, a flexible and interpretable recommendation simulator that can help accelerate research in interactive and data-driven recommender systems. We demonstrate its usefulness by studying existing methods within nine diverse environments derived from SARDINE, and even uncover novel insights about them.<\/jats:p>","DOI":"10.1145\/3656481","type":"journal-article","created":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T12:10:53Z","timestamp":1712578253000},"page":"1-34","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["SARDINE: Simulator for Automated Recommendation in Dynamic and Interactive Environments"],"prefix":"10.1145","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8265-9092","authenticated-orcid":false,"given":"Romain","family":"Deffayet","sequence":"first","affiliation":[{"name":"Naver Labs Europe, Meylan, France and University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0302-0376","authenticated-orcid":false,"given":"Thibaut","family":"Thonet","sequence":"additional","affiliation":[{"name":"Naver Labs Europe, Meylan, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6471-5208","authenticated-orcid":false,"given":"Dongyoon","family":"Hwang","sequence":"additional","affiliation":[{"name":"KAIST, Daejeon, Korea (the Republic of)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6512-283X","authenticated-orcid":false,"given":"Vassilissa","family":"Lehoux","sequence":"additional","affiliation":[{"name":"Naver Labs Europe, Meylan, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7516-3707","authenticated-orcid":false,"given":"Jean-Michel","family":"Renders","sequence":"additional","affiliation":[{"name":"Naver Labs Europe, Meylan, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1086-0202","authenticated-orcid":false,"given":"Maarten","family":"de Rijke","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,6,5]]},"reference":[{"key":"e_1_3_3_2_2","first-page":"127","volume-title":"Proceedings of the 30th International Conference on Machine Learning (Proceedings of Machine Learning Research)","volume":"28","author":"Agrawal Shipra","year":"2013","unstructured":"Shipra Agrawal and Navin Goyal. 2013. Thompson sampling for contextual bandits with linear payoffs. In Proceedings of the 30th International Conference on Machine Learning (Proceedings of Machine Learning Research), Sanjoy Dasgupta and David McAllester (Eds.), Vol. 28. PMLR, 127\u2013135. Retrieved from https:\/\/proceedings.mlr.press\/v28\/agrawal13.html"},{"key":"e_1_3_3_3_2","doi-asserted-by":"crossref","first-page":"2155","DOI":"10.1145\/3366423.3380281","volume-title":"Proceedings of the Web Conference (WWW\u201920)","author":"Anderson Ashton","year":"2020","unstructured":"Ashton Anderson, Lucas Maystre, Ian Anderson, Rishabh Mehrotra, and Mounia Lalmas. 2020. Algorithmic effects on the diversity of consumption on spotify. In Proceedings of the Web Conference (WWW\u201920). ACM, New York, NY, 2155\u20132165. 10.1145\/3366423.3380281"},{"key":"e_1_3_3_4_2","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1145\/3604915.3608820","volume-title":"Proceedings of the 17th ACM Conference on Recommender Systems (RecSys\u201923)","author":"Chaimalas Iason","year":"2023","unstructured":"Iason Chaimalas, Duncan Martin Walker, Edoardo Gruppi, Benjamin Richard Clark, and Laura Toni. 2023. Bootstrapped personalized popularity for cold start recommender systems. In Proceedings of the 17th ACM Conference on Recommender Systems (RecSys\u201923). ACM, New York, NY, 715\u2013722. 10.1145\/3604915.3608820"},{"key":"e_1_3_3_5_2","first-page":"1","volume-title":"IEEE International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE\u201914)","author":"Quba Rana Chamsi Abu","year":"2014","unstructured":"Rana Chamsi Abu Quba, Salima Hassas, Hammam Chamsi, and Usama Fayyad. 2014. From a \u201ccold\u201d to a \u201cwarm\u201d start in recommender systems. In IEEE International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE\u201914). IEEE Digital Library, 1\u20137. 10.1109\/WETICE.2014.66"},{"key":"e_1_3_3_6_2","first-page":"456","volume-title":"Proceedings of the 13th International Conference on Web Search and Data Mining (WSDM\u201919)","author":"Chen Minmin","year":"2019","unstructured":"Minmin Chen, Alex Beutel, Paul Covington, Sagar Jain, Francois Belletti, and Ed H. Chi. 2019. Top-k off-policy correction for a REINFORCE recommender system. In Proceedings of the 13th International Conference on Web Search and Data Mining (WSDM\u201919). 456\u2013464. 10.1145\/3289600.3290999"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.2200\/S00654ED1V01Y201507ICR043"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v16i1.19275"},{"key":"e_1_3_3_9_2","first-page":"87","volume-title":"Proceedings of the International Conference on Web Search and Data Mining (WSDM\u201908)","author":"Craswell Nick","year":"2008","unstructured":"Nick Craswell, Onno Zoeter, Michael Taylor, and Bill Ramsey. 2008. An experimental comparison of click position-bias models. In Proceedings of the International Conference on Web Search and Data Mining (WSDM\u201908). ACM, New York, NY, 87\u201394. 10.1145\/1341531.1341545"},{"key":"e_1_3_3_10_2","first-page":"558","volume-title":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201923)","author":"Deffayet Romain","year":"2023","unstructured":"Romain Deffayet, Philipp Hager, Jean-Michel Renders, and Maarten de Rijke. 2023. An offline metric for the debiasedness of click models. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201923). ACM, New York, NY, 558\u2013568. 10.1145\/3539618.3591639"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582900.3582905"},{"key":"e_1_3_3_12_2","first-page":"580","volume-title":"Proceedings of the 16th ACM International Conference on Web Search and Data Mining (WSDM\u201923)","author":"Deffayet Romain","year":"2023","unstructured":"Romain Deffayet, Thibaut Thonet, Jean-Michel Renders, and Maarten de Rijke. 2023. Generative slate recommendation with reinforcement learning. In Proceedings of the 16th ACM International Conference on Web Search and Data Mining (WSDM\u201923). ACM, New York, NY, 580\u2013588. 10.1145\/3539597.3570412"},{"key":"e_1_3_3_13_2","first-page":"238","volume-title":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201923)","author":"Gao Chongming","year":"2023","unstructured":"Chongming Gao, Kexin Huang, Jiawei Chen, Yuan Zhang, Biao Li, Peng Jiang, Shiqi Wang, Zhong Zhang, and Xiangnan He. 2023. Alleviating matthew effect of offline reinforcement learning in interactive recommendation. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201923). ACM, New York, NY, 238\u2013248. 10.1145\/3539618.3591636"},{"key":"e_1_3_3_14_2","first-page":"3440","volume-title":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201923)","author":"Gupta Shashank","year":"2023","unstructured":"Shashank Gupta, Philipp Hager, Jin Huang, Ali Vardasbi, and Harrie Oosterhuis. 2023. Recent advances in the foundations and applications of unbiased learning to rank. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201923). ACM, New York, NY, 3440\u20133443. 10.1145\/3539618.3594247"},{"key":"e_1_3_3_15_2","first-page":"1856","volume-title":"Proceedings of the International Conference on Machine Learning (ICML\u201918)","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In Proceedings of the International Conference on Machine Learning (ICML\u201918). 1856\u20131865. Retrieved from https:\/\/proceedings.mlr.press\/v80\/haarnoja18b.html."},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.02.013"},{"key":"e_1_3_3_17_2","volume-title":"Proceedings of the 4th International Conference on Learning Representations (ICLR\u201916)","author":"Hidasi Bal\u00e1zs","year":"2016","unstructured":"Bal\u00e1zs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2016. Session-based recommendations with recurrent neural networks. In Proceedings of the 4th International Conference on Learning Representations (ICLR\u201916). Retrieved from http:\/\/arxiv.org\/abs\/1511.06939."},{"key":"e_1_3_3_18_2","first-page":"2738","volume-title":"Proceedings of the ACM SIGIR International Conference (SIGIR\u201922)","author":"Huang Jin","year":"2022","unstructured":"Jin Huang, Harrie Oosterhuis, Bunyamin Cetinkaya, Thijs Rood, and Maarten de Rijke. 2022. State encoders in reinforcement learning for recommendation: A reproducibility study. In Proceedings of the ACM SIGIR International Conference (SIGIR\u201922). 2738\u20132748. 10.1145\/3477495.3531716"},{"key":"e_1_3_3_19_2","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1145\/3383313.3412252","volume-title":"Proceedings of the 14th ACM Conference on Recommender Systems (RecSys\u201920)","author":"Huang Jin","year":"2020","unstructured":"Jin Huang, Harrie Oosterhuis, Maarten de Rijke, and Herke van Hoof. 2020. Keeping dataset biases out of the simulation: A debiased simulator for reinforcement learning based recommender systems. In Proceedings of the 14th ACM Conference on Recommender Systems (RecSys\u201920). ACM, New York, NY, 190\u2013199. 10.1145\/3383313.3412252"},{"key":"e_1_3_3_20_2","first-page":"1432","volume-title":"Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research)","volume":"130","author":"Huleihel Wasim","year":"2021","unstructured":"Wasim Huleihel, Soumyabrata Pal, and Ofer Shayevitz. 2021. Learning user preferences in non-stationary environments. In Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research), Arindam Banerjee and Kenji Fukumizu (Eds.), Vol. 130. PMLR, 1432\u20131440. Retrieved from https:\/\/proceedings.mlr.press\/v130\/huleihel21a.html."},{"key":"e_1_3_3_21_2","first-page":"2592","volume-title":"Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI\u201919)","author":"Ie Eugene","year":"2019","unstructured":"Eugene Ie, Vihan Jain, Jing Wang, Sanmit Narvekar, Ritesh Agarwal, Rui Wu, Heng-Tze Cheng, Tushar Chandra, and Craig Boutilier. 2019. SlateQ: A tractable decomposition for reinforcement learning with recommendation sets. In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI\u201919). International Joint Conferences on Artificial Intelligence Organization, 2592\u20132599. 10.24963\/ijcai.2019\/360"},{"key":"e_1_3_3_22_2","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. Retrieved from https:\/\/arxiv:cs.LG\/1909.04847"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/2891406"},{"key":"e_1_3_3_24_2","volume-title":"Proceedings of the PERSPECTIVES Workshop at RecSys\u201923","author":"Jeunen Olivier","year":"2023","unstructured":"Olivier Jeunen. 2023. A common misassumption in online experiments with machine learning models. In Proceedings of the PERSPECTIVES Workshop at RecSys\u201923. Retrieved from https:\/\/arxiv.org\/abs\/2304.10900."},{"key":"e_1_3_3_25_2","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1145\/3018661.3018699","volume-title":"Proceedings of the International Conference on Web Search and Data Mining (WSDM\u201917)","author":"Joachims Thorsten","year":"2017","unstructured":"Thorsten Joachims, Adith Swaminathan, and Tobias Schnabel. 2017. Unbiased learning-to-rank with biased feedback. In Proceedings of the International Conference on Web Search and Data Mining (WSDM\u201917). 781\u2013789. 10.1145\/3018661.3018699"},{"key":"e_1_3_3_26_2","unstructured":"Haruka Kiyohara Ren Kishimoto Kosuke Kawakami Ken Kobayashi Kazuhide Nataka and Yuta Saito. 2023. SCOPE-RL: A python library for offline reinforcement learning off-policy evaluation and policy selection. Retrieved from https:\/\/github.com\/hakuhodo-technologies\/scope-rl"},{"key":"e_1_3_3_27_2","volume-title":"Proceedings of the ACM Conference on Recommender Systems (RecSys\u201923)","author":"Knyazev Norman","year":"2023","unstructured":"Norman Knyazev and Harrie Oosterhuis. 2023. A lightweight method for modeling confidence in recommendations with learned beta distributions. In Proceedings of the ACM Conference on Recommender Systems (RecSys\u201923). ACM, New York, NY. Retrieved from https:\/\/arxiv.org\/abs\/2308.03186"},{"key":"e_1_3_3_28_2","first-page":"2607","volume-title":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201922)","author":"Lee Hojoon","year":"2022","unstructured":"Hojoon Lee, Dongyoon Hwang, Kyushik Min, and Jaegul Choo. 2022. Towards validating long-term user feedbacks in interactive recommendation systems. In Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201922). 2607\u20132611. 10.48550\/arXiv.2308.11137"},{"key":"e_1_3_3_29_2","first-page":"661","volume-title":"Proceedings of the 19th International Conference on World Wide Web (WWW\u201910)","author":"Li Lihong","year":"2010","unstructured":"Lihong Li, Wei Chu, John Langford, and Robert E. Schapire. 2010. A contextual-bandit approach to personalized news article recommendation. In Proceedings of the 19th International Conference on World Wide Web (WWW\u201910). ACM, New York, NY, 661\u2013670. 10.1145\/1772690.1772758"},{"key":"e_1_3_3_30_2","volume-title":"Proceedings of the 4th International Conference on Learning Representations (ICLR\u201916)","author":"Lillicrap Timothy P.","year":"2016","unstructured":"Timothy P. Lillicrap, Jonathan J. Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. 2016. Continuous control with deep reinforcement learning. In Proceedings of the 4th International Conference on Learning Representations (ICLR\u201916)."},{"key":"e_1_3_3_31_2","first-page":"833","volume-title":"Proceedings of the International Conference on World Wide Web(WWW\u201923)","author":"Liu Shuchang","year":"2023","unstructured":"Shuchang Liu, Qingpeng Cai, Bowen Sun, Yuhao Wang, Ji Jiang, Dong Zheng, Peng Jiang, Kun Gai, Xiangyu Zhao, and Yongfeng Zhang. 2023. Exploration and regularization of the latent action space in recommendation. In Proceedings of the International Conference on World Wide Web(WWW\u201923). 833\u2013844. 10.1145\/3543507.3583244"},{"key":"e_1_3_3_32_2","first-page":"3656","volume-title":"Proceedings of the International Joint Conference on Neural Networks (IJCNN\u201917)","author":"Majumdar Angshul","year":"2017","unstructured":"Angshul Majumdar and Anant Jain. 2017. Cold-start, warm-start and everything in between: An autoencoder based approach to recommendation. In Proceedings of the International Joint Conference on Neural Networks (IJCNN\u201917). 3656\u20133663. 10.1109\/IJCNN.2017.7966316"},{"key":"e_1_3_3_33_2","unstructured":"Tatsuya Matsushima Hiroki Furuta Yutaka Matsuo Ofir Nachum and Shixiang Gu. 2020. Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization. Retrieved from https:\/\/arxiv:cs.LG\/2006.03647"},{"key":"e_1_3_3_34_2","doi-asserted-by":"crossref","first-page":"1097","DOI":"10.1145\/1125451.1125659","volume-title":"Proceedings of the CHI\u201906 Extended Abstracts on Human Factors in Computing Systems (CHI EA\u201906)","author":"McNee Sean M.","year":"2006","unstructured":"Sean M. McNee, John Riedl, and Joseph A. Konstan. 2006. Being accurate is not enough: How accuracy metrics have hurt recommender systems. In Proceedings of the CHI\u201906 Extended Abstracts on Human Factors in Computing Systems (CHI EA\u201906). ACM, New York, NY, 1097\u20131101. 10.1145\/1125451.1125659"},{"key":"e_1_3_3_35_2","first-page":"3996","volume-title":"Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM\u201921)","author":"Mehrotra Rishabh","year":"2021","unstructured":"Rishabh Mehrotra. 2021. Algorithmic balancing of familiarity, similarity, & discovery in music recommendations. In Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM\u201921). ACM, New York, NY, 3996\u20134005. 10.1145\/3459637.3481893"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30164-8_705"},{"key":"e_1_3_3_37_2","first-page":"1023","volume-title":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201921)","author":"Oosterhuis Harrie","year":"2021","unstructured":"Harrie Oosterhuis. 2021. Computationally efficient optimization of Plackett-Luce ranking models for relevance and fairness. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201921). ACM, New York, NY, 1023\u20131032. 10.1145\/3404835.3462830"},{"key":"e_1_3_3_38_2","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1145\/3442381.3450018","volume-title":"Proceedings of the Web Conference (WWW\u201921)","author":"Oosterhuis Harrie","year":"2021","unstructured":"Harrie Oosterhuis and Maarten de Rijke. 2021. Robust generalization and safe query-specialization in counterfactual learning to rank. In Proceedings of the Web Conference (WWW\u201921). ACM, New York, NY, 158\u2013170. 10.1145\/3442381.3450018"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01758-5"},{"key":"e_1_3_3_40_2","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. Retrieved from https:\/\/arxiv:cs.IR\/1808.00720"},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7637-6_24"},{"key":"e_1_3_3_42_2","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks","volume":"1","author":"Saito Yuta","year":"2021","unstructured":"Yuta Saito, Shunsuke Aihara, Megumi Matsutani, and Yusuke Narita. 2021. Open bandit dataset and pipeline: Towards realistic and reproducible off-policy evaluation. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, J. Vanschoren and S. Yeung (Eds.), Vol. 1. Curran. Retrieved from https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/33e75ff09dd601bbe69f351039152189-Paper-round2.pdf"},{"key":"e_1_3_3_43_2","unstructured":"Otmane Sakhi David Rohde and Nicolas Chopin. 2023. Fast Slate Policy Optimization: Going Beyond Plackett-Luce. Retrieved from https:\/\/arxiv:cs.LG\/2308.01566"},{"key":"e_1_3_3_44_2","first-page":"189","volume-title":"Proceedings of the International Conference on Data Mining Workshops (ICDMW\u201920)","author":"Santana Marlesson R. O.","year":"2020","unstructured":"Marlesson R. O. Santana, Luckeciano C. Melo, Fernando H. F. Camargo, Bruno Brand\u00e3o, Anderson Soares, Renan M. Oliveira, and Sandor Caetano. 2020. MARS-Gym: A gym framework to model, train, and evaluate recommender systems for marketplaces. In Proceedings of the International Conference on Data Mining Workshops (ICDMW\u201920). 189\u2013197. 10.1109\/ICDMW51313.2020.00035"},{"key":"e_1_3_3_45_2","first-page":"96","volume-title":"Proceedings of the 15th ACM Conference on Recommender Systems (RecSys\u201921)","author":"Sato Masahiro","year":"2021","unstructured":"Masahiro Sato. 2021. Online evaluation methods for the causal effect of recommendations. In Proceedings of the 15th ACM Conference on Recommender Systems (RecSys\u201921). ACM, New York, NY, 96\u2013101. 10.1145\/3460231.3474235"},{"key":"e_1_3_3_46_2","volume-title":"The Stanford Encyclopedia of Philosophy (Spring 2022 ed.)","author":"Sequoiah-Grayson Sebastian","year":"2022","unstructured":"Sebastian Sequoiah-Grayson and Luciano Floridi. 2022. Semantic conceptions of information. In The Stanford Encyclopedia of Philosophy (Spring 2022 ed.), Edward N. Zalta (Ed.). Metaphysics Research Lab, Stanford University."},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116669"},{"key":"e_1_3_3_49_2","first-page":"2629","volume-title":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201923)","author":"Sun Aixin","year":"2023","unstructured":"Aixin Sun. 2023. Take a fresh look at recommender systems from an evaluation standpoint. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201923). ACM, New York, NY, 2629\u20132638. 10.1145\/3539618.3591931"},{"key":"e_1_3_3_50_2","first-page":"3635","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS\u201917)","author":"Swaminathan Adith","year":"2017","unstructured":"Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal, Miroslav Dud\u00edk, John Langford, Damien Jose, and Imed Zitouni. 2017. Off-policy evaluation for slate recommendation. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS\u201917). Curran Associates, Red Hook, NY, 3635\u20133645."},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","unstructured":"Mark Towers Jordan K. Terry Ariel Kwiatkowski John U. Balis Gianluca de Cola Tristan Deleu Manuel Goul\u00e3o Andreas Kallinteris Arjun K.G. Markus Krimmel Rodrigo Perez-Vicente Andrea Pierr\u00e9 Sander Schulhoff Jun Jet Tai Andrew Tan Jin Shen and Omar G. Younis. 2023. Gymnasium. Retrieved from https:\/\/zenodo.org\/records\/8127026 10.5281\/zenodo.8127026","DOI":"10.5281\/zenodo.8127026"},{"key":"e_1_3_3_52_2","first-page":"2935","volume-title":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201923)","author":"Wang Kai","year":"2023","unstructured":"Kai Wang, Zhene Zou, Minghao Zhao, Qilin Deng, Yue Shang, Yile Liang, Runze Wu, Xudong Shen, Tangjie Lyu, and Changjie Fan. 2023. RL4RS: A real-world dataset for reinforcement learning based recommender system. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201923). ACM, New York, NY, 2935\u20132944. 10.1145\/3539618.3591899"},{"key":"e_1_3_3_53_2","unstructured":"Liyuan Wang Xingxing Zhang Hang Su and Jun Zhu. 2023. A Comprehensive Survey of Continual Learning: Theory Method and Application. Retrieved from https:\/\/arxiv:cs.LG\/2302.00487"},{"key":"e_1_3_3_54_2","doi-asserted-by":"crossref","first-page":"2015","DOI":"10.1145\/3485447.3512202","volume-title":"Proceedings of the ACM Web Conference (WWW\u201922)","author":"Wang Yu","year":"2022","unstructured":"Yu Wang, Xin Xin, Zaiqiao Meng, Joemon M. Jose, Fuli Feng, and Xiangnan He. 2022. Learning robust recommenders through cross-model agreement. In Proceedings of the ACM Web Conference (WWW\u201922). ACM, New York, NY, 2015\u20132025. 10.1145\/3485447.3512202"},{"key":"e_1_3_3_55_2","first-page":"1347","volume-title":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201922)","author":"Xin Xin","year":"2022","unstructured":"Xin Xin, Tiago Pimentel, Alexandros Karatzoglou, Pengjie Ren, Konstantina Christakopoulou, and Zhaochun Ren. 2022. Rethinking reinforcement learning for recommendation: A prompt perspective. In Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201922). ACM, New York, NY, 1347\u20131357. 10.1145\/3477495.3531714"},{"key":"e_1_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3556536"}],"container-title":["ACM Transactions on Recommender Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3656481","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3656481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:57:31Z","timestamp":1750291051000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3656481"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,5]]},"references-count":55,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,9,30]]}},"alternative-id":["10.1145\/3656481"],"URL":"https:\/\/doi.org\/10.1145\/3656481","relation":{},"ISSN":["2770-6699"],"issn-type":[{"value":"2770-6699","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,5]]},"assertion":[{"value":"2023-09-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-27","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}