{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:35:43Z","timestamp":1783737343067,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-sa\/4.0\/"}],"funder":[{"name":"Natural Science Foundation of China","award":["U21B2026, 62372399, 62372260"],"award-info":[{"award-number":["U21B2026, 62372399, 62372260"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657868","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"977-987","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["EasyRL4Rec: An Easy-to-use Library for Reinforcement Learning Based Recommender Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2942-1576","authenticated-orcid":false,"given":"Yuanqing","family":"Yu","sequence":"first","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5187-9196","authenticated-orcid":false,"given":"Chongming","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4752-2629","authenticated-orcid":false,"given":"Jiawei","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7933-8706","authenticated-orcid":false,"given":"Heng","family":"Tang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7041-7470","authenticated-orcid":false,"given":"Yuefeng","family":"Sun","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8219-2821","authenticated-orcid":false,"given":"Qian","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5604-7527","authenticated-orcid":false,"given":"Weizhi","family":"Ma","sequence":"additional","affiliation":[{"name":"AIR, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3158-1920","authenticated-orcid":false,"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Finite-time analysis of the multiarmed bandit problem. Machine learning","author":"Auer Peter","year":"2002","unstructured":"Peter Auer, Nicolo Cesa-Bianchi, and Paul Fischer. 2002. Finite-time analysis of the multiarmed bandit problem. Machine learning, Vol. 47 (2002), 235--256."},{"key":"e_1_3_2_1_2_1","volume-title":"REVEAL 18","author":"Barraza-Urbina Andrea","year":"2018","unstructured":"Andrea Barraza-Urbina, Georgia Koutrika, Mathieu d'Aquin, and Conor Hayes. 2018. BEARS: Towards an evaluation framework for bandit-based interactive recommender systems. REVEAL 18, October 6-7, 2018, Vancouver, Canada (2018)."},{"key":"e_1_3_2_1_3_1","volume-title":"International conference on machine learning. PMLR, 449--458","author":"Bellemare Marc G","year":"2017","unstructured":"Marc G Bellemare, Will Dabney, and R\u00e9mi Munos. 2017. A distributional perspective on reinforcement learning. In International conference on machine learning. PMLR, 449--458."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3584640"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583259"},{"key":"e_1_3_2_1_6_1","volume-title":"An empirical evaluation of thompson sampling. Advances in neural information processing systems","author":"Chapelle Olivier","year":"2011","unstructured":"Olivier Chapelle and Lihong Li. 2011. An empirical evaluation of thompson sampling. Advances in neural information processing systems, Vol. 24 (2011)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462919"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3522672"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546758"},{"key":"e_1_3_2_1_11_1","volume-title":"Deep reinforcement learning from human preferences. Advances in neural information processing systems","author":"Christiano Paul F","year":"2017","unstructured":"Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_12_1","volume-title":"Filter bubbles, echo chambers, and online news consumption. Public opinion quarterly","author":"Flaxman Seth","year":"2016","unstructured":"Seth Flaxman, Sharad Goel, and Justin M Rao. 2016. Filter bubbles, echo chambers, and online news consumption. Public opinion quarterly, Vol. 80, S1 (2016), 298--320."},{"key":"e_1_3_2_1_13_1","volume-title":"Benchmarking batch deep reinforcement learning algorithms. arXiv preprint arXiv:1910.01708","author":"Fujimoto Scott","year":"2019","unstructured":"Scott Fujimoto, Edoardo Conti, Mohammad Ghavamzadeh, and Joelle Pineau. 2019. Benchmarking batch deep reinforcement learning algorithms. arXiv preprint arXiv:1910.01708 (2019)."},{"key":"e_1_3_2_1_14_1","volume-title":"International conference on machine learning. PMLR, 1587--1596","author":"Fujimoto Scott","year":"2018","unstructured":"Scott Fujimoto, Herke Hoof, and David Meger. 2018. Addressing function approximation error in actor-critic methods. In International conference on machine learning. PMLR, 1587--1596."},{"key":"e_1_3_2_1_15_1","volume-title":"International conference on machine learning. PMLR","author":"Fujimoto Scott","year":"2019","unstructured":"Scott Fujimoto, David Meger, and Doina Precup. 2019. Off-policy deep reinforcement learning without exploration. In International conference on machine learning. PMLR, 2052--2062."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591636"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557220"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557624"},{"key":"e_1_3_2_1_19_1","volume-title":"CIRS: Bursting filter bubbles by counterfactual interactive recommender system. ACM Transactions on Information Systems","author":"Gao Chongming","year":"2022","unstructured":"Chongming Gao, Shiqi Wang, Shijun Li, Jiawei Chen, Xiangnan He, Wenqiang Lei, Biao Li, Yuan Zhang, and Peng Jiang. 2022. CIRS: Bursting filter bubbles by counterfactual interactive recommender system. ACM Transactions on Information Systems (2022)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172127"},{"key":"e_1_3_2_1_21_1","volume-title":"Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939","author":"Hidasi Bal\u00e1zs","year":"2015","unstructured":"Bal\u00e1zs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2015. Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939 (2015)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412252"},{"key":"e_1_3_2_1_23_1","volume-title":"Recsim: A configurable simulation platform for recommender systems. arXiv preprint arXiv:1909.04847","author":"Ie Eugene","year":"2019","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)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_26_1","volume-title":"Advances in Neural Information Processing Systems","author":"Konda Vijay","year":"1999","unstructured":"Vijay Konda and John Tsitsiklis. 1999. Actor-Critic Algorithms. In Advances in Neural Information Processing Systems, S. Solla, T. Leen, and K. M\u00fcller (Eds.), Vol. 12. MIT Press. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/1999\/file\/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401944"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_1_29_1","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar Aviral","year":"2020","unstructured":"Aviral Kumar, Aurick Zhou, George Tucker, and Sergey Levine. 2020. Conservative q-learning for offline reinforcement learning. Advances in Neural Information Processing Systems, Vol. 33 (2020), 1179--1191.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_1_31_1","volume-title":"RLlib: Abstractions for Distributed Reinforcement Learning. In International Conference on Machine Learning (ICML).","author":"Liang Eric","year":"2018","unstructured":"Eric Liang, Richard Liaw, Robert Nishihara, Philipp Moritz, Roy Fox, Ken Goldberg, Joseph E. Gonzalez, Michael I. Jordan, and Ion Stoica. 2018. RLlib: Abstractions for Distributed Reinforcement Learning. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_32_1","volume-title":"Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971","author":"Lillicrap Timothy P","year":"2015","unstructured":"Timothy P Lillicrap, Jonathan J Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. 2015. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106170"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583244"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412152"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1639714.1639717"},{"key":"e_1_3_2_1_37_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591656"},{"key":"e_1_3_2_1_39_1","volume-title":"Recogym: A reinforcement learning environment for the problem of product recommendation in online advertising. arXiv preprint arXiv:1808.00720","author":"Rohde David","year":"2018","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)."},{"key":"e_1_3_2_1_40_1","volume-title":"Open bandit dataset and pipeline: Towards realistic and reproducible off-policy evaluation. arXiv preprint arXiv:2008.07146","author":"Saito Yuta","year":"2020","unstructured":"Yuta Saito, Shunsuke Aihara, Megumi Matsutani, and Yusuke Narita. 2020. Open bandit dataset and pipeline: Towards realistic and reproducible off-policy evaluation. arXiv preprint arXiv:2008.07146 (2020)."},{"key":"e_1_3_2_1_41_1","volume-title":"The adaptive web","author":"Schafer J Ben","unstructured":"J Ben Schafer, Dan Frankowski, Jon Herlocker, and Shilad Sen. 2007. Collaborative filtering recommender systems. In The adaptive web. Springer, 291--324."},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning","author":"Schnabel Tobias","year":"2016","unstructured":"Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak, and Thorsten Joachims. 2016. Recommendations as Treatments: Debiasing Learning and Evaluation. In Proceedings of the 33rd International Conference on International Conference on Machine Learning (New York, NY, USA). JMLR.org, 1670--1679."},{"key":"e_1_3_2_1_43_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_44_1","article-title":"An MDP-based recommender system","volume":"6","author":"Shani Guy","year":"2005","unstructured":"Guy Shani, David Heckerman, Ronen I Brafman, and Craig Boutilier. 2005. An MDP-based recommender system. Journal of Machine Learning Research, Vol. 6, 9 (2005).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531754"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2019.00129"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159656"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16111-7_23"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.8127026"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591899"},{"key":"e_1_3_2_1_52_1","first-page":"7768","article-title":"Critic regularized regression","volume":"33","author":"Wang Ziyu","year":"2020","unstructured":"Ziyu Wang, Alexander Novikov, Konrad Zolna, Josh S Merel, Jost Tobias Springenberg, Scott E Reed, Bobak Shahriari, Noah Siegel, Caglar Gulcehre, Nicolas Heess, et al. 2020. Critic regularized regression. Advances in Neural Information Processing Systems, Vol. 33 (2020), 7768--7778.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_53_1","first-page":"1","article-title":"Tianshou: A Highly Modularized Deep Reinforcement Learning Library","volume":"23","author":"Weng Jiayi","year":"2022","unstructured":"Jiayi Weng, Huayu Chen, Dong Yan, Kaichao You, Alexis Duburcq, Minghao Zhang, Yi Su, Hang Su, and Jun Zhu. 2022. Tianshou: A Highly Modularized Deep Reinforcement Learning Library. Journal of Machine Learning Research, Vol. 23, 267 (2022), 1--6. http:\/\/jmlr.org\/papers\/v23\/21--1127.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_54_1","volume-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning. Reinforcement learning","author":"Williams Ronald J","year":"1992","unstructured":"Ronald J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Reinforcement learning (1992), 5--32."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401147"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557300"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599473"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290975"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539040"},{"key":"e_1_3_2_1_60_1","volume-title":"KuaiSim: A comprehensive simulator for recommender systems. arXiv preprint arXiv:2309.12645","author":"Zhao Kesen","year":"2023","unstructured":"Kesen Zhao, Shuchang Liu, Qingpeng Cai, Xiangyu Zhao, Ziru Liu, Dong Zheng, Peng Jiang, and Kun Gai. 2023. KuaiSim: A comprehensive simulator for recommender systems. arXiv preprint arXiv:2309.12645 (2023)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657868","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657868","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:30:46Z","timestamp":1755840646000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657868"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":63,"alternative-id":["10.1145\/3626772.3657868","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657868","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}