{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:09:45Z","timestamp":1750219785454,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3592022","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:23Z","timestamp":1689726143000},"page":"2179-2183","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Model-free Reinforcement Learning with Stochastic Reward Stabilization for Recommender Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1503-6519","authenticated-orcid":false,"given":"Tianchi","family":"Cai","sequence":"first","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1439-3170","authenticated-orcid":false,"given":"Shenliao","family":"Bao","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1083-2834","authenticated-orcid":false,"given":"Jiyan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0666-0769","authenticated-orcid":false,"given":"Shiji","family":"Zhou","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3796-161X","authenticated-orcid":false,"given":"Wenpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0706-3448","authenticated-orcid":false,"given":"Lihong","family":"Gu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7596-4945","authenticated-orcid":false,"given":"Jinjie","family":"Gu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7091-2318","authenticated-orcid":false,"given":"Guannan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Reinforcement learning based recommender systems: A survey. ACM Computing Surveys (CSUR)","author":"Afsar M Mehdi","year":"2021","unstructured":"M Mehdi Afsar, Trafford Crump, and Behrouz Far. 2021. Reinforcement learning based recommender systems: A survey. ACM Computing Surveys (CSUR) (2021)."},{"key":"e_1_3_2_1_2_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Bai Xueying","year":"2019","unstructured":"Xueying Bai, Jian Guan, and Hongning Wang. 2019. A model-based reinforcement learning with adversarial training for online recommendation. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570486"},{"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\/3437963.3441764"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546758"},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Machine Learning. PMLR, 1052--1061","author":"Chen Xinshi","year":"2019","unstructured":"Xinshi Chen, Shuang Li, Hui Li, Shaohua Jiang, Yuan Qi, and Le Song. 2019b. Generative adversarial user model for reinforcement learning based recommendation system. In International Conference on Machine Learning. PMLR, 1052--1061."},{"key":"e_1_3_2_1_9_1","volume-title":"A survey of deep reinforcement learning in recommender systems: A systematic review and future directions. arXiv preprint arXiv:2109.03540","author":"Chen Xiaocong","year":"2021","unstructured":"Xiaocong Chen, Lina Yao, Julian McAuley, Guanglin Zhou, and Xianzhi Wang. 2021b. A survey of deep reinforcement learning in recommender systems: A systematic review and future directions. arXiv preprint arXiv:2109.03540 (2021)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531796"},{"key":"e_1_3_2_1_13_1","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412233"},{"key":"e_1_3_2_1_15_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_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505665"},{"key":"e_1_3_2_1_17_1","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. (2019)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3109859.3109872"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403175"},{"key":"e_1_3_2_1_20_1","unstructured":"Lukasz Kaiser Mohammad Babaeizadeh Piotr Milos Blazej Osinski Roy H Campbell Konrad Czechowski Dumitru Erhan Chelsea Finn Piotr Kozakowski Sergey Levine et al. 2019. Model-based reinforcement learning for atari. arXiv preprint arXiv:1903.00374 (2019)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_1_22_1","volume-title":"Advances in collaborative filtering. Recommender systems handbook","author":"Koren Yehuda","year":"2022","unstructured":"Yehuda Koren, Steffen Rendle, and Robert Bell. 2022. Advances in collaborative filtering. Recommender systems handbook (2022), 91--142."},{"key":"e_1_3_2_1_23_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_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107085"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371858"},{"key":"e_1_3_2_1_26_1","volume-title":"Deep reinforcement learning based recommendation with explicit user-item interactions modeling. arXiv preprint arXiv:1810.12027","author":"Liu Feng","year":"2018","unstructured":"Feng Liu, Ruiming Tang, Xutao Li, Weinan Zhang, Yunming Ye, Haokun Chen, Huifeng Guo, and Yuzhou Zhang. 2018. Deep reinforcement learning based recommendation with explicit user-item interactions modeling. arXiv preprint arXiv:1810.12027 (2018)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2488200"},{"key":"e_1_3_2_1_28_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_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2168752.2168771"},{"key":"e_1_3_2_1_30_1","volume-title":"Nature","volume":"588","author":"Schrittwieser Julian","year":"2020","unstructured":"Julian Schrittwieser, Ioannis Antonoglou, Thomas Hubert, Karen Simonyan, Laurent Sifre, Simon Schmitt, Arthur Guez, Edward Lockhart, Demis Hassabis, Thore Graepel, et al. 2020. Mastering atari, go, chess and shogi by planning with a learned model. Nature, Vol. 588, 7839 (2020), 604--609."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S","key":"e_1_3_2_1_32_1","unstructured":"Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_1_33_1","volume-title":"Deep reinforcement learning with double q-learning. arXiv preprint arXiv:1509.06461","author":"Hasselt Hado Van","year":"2015","unstructured":"Hado Van Hasselt, Arthur Guez, and David Silver. 2015. Deep reinforcement learning with double q-learning. arXiv preprint arXiv:1509.06461 (2015)."},{"key":"e_1_3_2_1_34_1","volume-title":"International conference on machine learning. PMLR","author":"Wang Ziyu","year":"2016","unstructured":"Ziyu Wang, Tom Schaul, Matteo Hessel, Hado Hasselt, Marc Lanctot, and Nando Freitas. 2016. Dueling network architectures for deep reinforcement learning. In International conference on machine learning. PMLR, 1995--2003."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16579"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401147"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i17.17760"},{"key":"e_1_3_2_1_38_1","volume-title":"Improving sequential recommendation consistency with self-supervised imitation. arXiv preprint arXiv:2106.14031","author":"Yuan Xu","year":"2021","unstructured":"Xu Yuan, Hongshen Chen, Yonghao Song, Xiaofang Zhao, Zhuoye Ding, Zhen He, and Bo Long. 2021. Improving sequential recommendation consistency with self-supervised imitation. arXiv preprint arXiv:2106.14031 (2021)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16156"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412044"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330668"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371801"}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Taipei Taiwan","acronym":"SIGIR '23"},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3592022","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3592022","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:49Z","timestamp":1750178269000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3592022"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":45,"alternative-id":["10.1145\/3539618.3592022","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3592022","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}