{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:45:52Z","timestamp":1783611952384,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,2,11]],"date-time":"2022-02-11T00:00:00Z","timestamp":1644537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072279"],"award-info":[{"award-number":["62072279"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,2,11]]},"DOI":"10.1145\/3488560.3498494","type":"proceedings-article","created":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T21:42:57Z","timestamp":1644961377000},"page":"1186-1196","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["Supervised Advantage Actor-Critic for Recommender Systems"],"prefix":"10.1145","author":[{"given":"Xin","family":"Xin","sequence":"first","affiliation":[{"name":"Shandong University, Qingdao City, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandros","family":"Karatzoglou","sequence":"additional","affiliation":[{"name":"Google Research, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ioannis","family":"Arapakis","sequence":"additional","affiliation":[{"name":"Telefonica Research, Barcelona, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joemon M.","family":"Jose","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, Scotland Uk"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,2,15]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"e_1_3_2_2_2_1","volume-title":"Generative Adversarial User Model for Reinforcement Learning Based Recommendation System. In International Conference on Machine Learning . 1052--1061","author":"Chen Xinshi","year":"2019","unstructured":"Xinshi Chen, Shuang Li, Hui Li, Shaohua Jiang, Yuan Qi, and Le Song. 2019 b. Generative Adversarial User Model for Reinforcement Learning Based Recommendation System. In International Conference on Machine Learning . 1052--1061."},{"key":"e_1_3_2_2_3_1","unstructured":"Chen Cheng Haiqin Yang Michael R Lyu and Irwin King. 2013. Where you like to go next: Successive point-of-interest recommendation. In Twenty-Third international joint conference on Artificial Intelligence ."},{"key":"e_1_3_2_2_4_1","volume-title":"International Conference on Machine Learning. 2052--2062","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. 2052--2062."},{"key":"e_1_3_2_2_5_1","volume-title":"Exact-K Recommendation via Maximal Clique Optimization. arXiv preprint arXiv:1905.07089","author":"Gong Yu","year":"2019","unstructured":"Yu Gong, Yu Zhu, Lu Duan, Qingwen Liu, Ziyu Guan, Fei Sun, Wenwu Ou, and Kenny Q Zhu. 2019. Exact-K Recommendation via Maximal Clique Optimization. arXiv preprint arXiv:1905.07089 (2019)."},{"key":"e_1_3_2_2_6_1","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672--2680."},{"key":"e_1_3_2_2_7_1","unstructured":"Hado V Hasselt. 2010. Double Q-learning. In Advances in Neural Information Processing Systems. 2613--2621."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0030"},{"key":"e_1_3_2_2_9_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_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-015-0417-y"},{"key":"e_1_3_2_2_11_1","unstructured":"Jonathan Ho and Stefano Ermon. 2016. Generative adversarial imitation learning. In Advances in neural information processing systems. 4565--4573."},{"key":"e_1_3_2_2_12_1","volume-title":"International Conference on Machine Learning. 2760--2769","author":"Ho Jonathan","year":"2016","unstructured":"Jonathan Ho, Jayesh Gupta, and Stefano Ermon. 2016. Model-free imitation learning with policy optimization. In International Conference on Machine Learning. 2760--2769."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219846"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.22"},{"key":"e_1_3_2_2_15_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_2_16_1","volume-title":"ACM Transactions on Information Systems (TOIS)","volume":"20","author":"Jaana Kalervo","year":"2002","unstructured":"Kalervo J\"arvelin and Jaana Kek\"al\"ainen. 2002. Cumulated gain-based evaluation of IR techniques. ACM Transactions on Information Systems (TOIS) , Vol. 20, 4 (2002), 422--446."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_2_18_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346998"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102780"},{"key":"e_1_3_2_2_23_1","volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)."},{"key":"e_1_3_2_2_24_1","volume-title":"Nature","volume":"518","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, et al. 2015. Human-level control through deep reinforcement learning. Nature , Vol. 518, 7540 (2015), 529."},{"key":"e_1_3_2_2_25_1","unstructured":"R\u00e9mi Munos Tom Stepleton Anna Harutyunyan and Marc Bellemare. 2016. Safe and efficient off-policy reinforcement learning. In Advances in Neural Information Processing Systems. 1054--1062."},{"key":"e_1_3_2_2_26_1","volume-title":"Aidan Clark, Seb Noury, et al.","author":"Parisotto Emilio","year":"2019","unstructured":"Emilio Parisotto, H Francis Song, Jack W Rae, Razvan Pascanu, Caglar Gulcehre, Siddhant M Jayakumar, Max Jaderberg, Raphael Lopez Kaufman, Aidan Clark, Seb Noury, et al. 2019. Stabilizing Transformers for Reinforcement Learning. arXiv preprint arXiv:1910.06764 (2019)."},{"key":"e_1_3_2_2_27_1","volume-title":"SQIL: Imitation learning via reinforcement learning with sparse rewards. arXiv preprint arXiv:1905.11108","author":"Reddy Siddharth","year":"2019","unstructured":"Siddharth Reddy, Anca D Dragan, and Sergey Levine. 2019. SQIL: Imitation learning via reinforcement learning with sparse rewards. arXiv preprint arXiv:1905.11108 (2019)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_2_29_1","volume-title":"Proceedings of the twenty-fifth conference on uncertainty in artificial intelligence. AUAI Press, 452--461","author":"Rendle Steffen","year":"2009","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. In Proceedings of the twenty-fifth conference on uncertainty in artificial intelligence. AUAI Press, 452--461."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772773"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2629350"},{"key":"e_1_3_2_2_32_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_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330933"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/1046920.1088715"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"e_1_3_2_2_36_1","volume-title":"Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al.","author":"Silver David","year":"2016","unstructured":"David Silver, Aja Huang, Chris J Maddison, Arthur Guez, Laurent Sifre, George Van Den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al. 2016. Mastering the game of Go with deep neural networks and tree search. nature , Vol. 529, 7587 (2016), 484."},{"key":"e_1_3_2_2_37_1","volume-title":"Curl: Contrastive unsupervised representations for reinforcement learning. arXiv preprint arXiv:2004.04136","author":"Srinivas Aravind","year":"2020","unstructured":"Aravind Srinivas, Michael Laskin, and Pieter Abbeel. 2020. Curl: Contrastive unsupervised representations for reinforcement learning. arXiv preprint arXiv:2004.04136 (2020)."},{"key":"e_1_3_2_2_38_1","volume-title":"Kakade","author":"Strehl Alex","year":"2010","unstructured":"Alex Strehl, John Langford, Lihong Li, and Sham M. Kakade. 2010. Learning from Logged Implicit Exploration Data. In NIPS ."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159656"},{"key":"e_1_3_2_2_40_1","volume-title":"Behavioral cloning from observation. arXiv preprint arXiv:1805.01954","author":"Torabi Faraz","year":"2018","unstructured":"Faraz Torabi, Garrett Warnell, and Peter Stone. 2018. Behavioral cloning from observation. arXiv preprint arXiv:1805.01954 (2018)."},{"key":"e_1_3_2_2_41_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_2_42_1","unstructured":"Nikos Vlassis Aur\u00e9lien Bibaut Maria Dimakopoulou and Tony Jebara. 2019. On the Design of Estimators for Bandit Off-Policy Evaluation. In ICML ."},{"key":"e_1_3_2_2_43_1","volume-title":"Self-Supervised Reinforcement Learning for Recommender Systems. SIGIR","author":"Xin Xin","year":"2020","unstructured":"Xin Xin, Alexandros Karatzoglou, Ioannis Arapakis, and Joemon M Jose. 2020. Self-Supervised Reinforcement Learning for Recommender Systems. SIGIR (2020)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290975"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_2_47_1","volume-title":"Reinforcement Learning to Optimize Long-term User Engagement in Recommender Systems. arXiv preprint arXiv:1902.05570","author":"Zou Lixin","year":"2019","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)."}],"event":{"name":"WSDM '22: The Fifteenth ACM International Conference on Web Search and Data Mining","location":"Virtual Event AZ USA","acronym":"WSDM '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488560.3498494","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3488560.3498494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:19Z","timestamp":1750188679000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488560.3498494"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,11]]},"references-count":47,"alternative-id":["10.1145\/3488560.3498494","10.1145\/3488560"],"URL":"https:\/\/doi.org\/10.1145\/3488560.3498494","relation":{},"subject":[],"published":{"date-parts":[[2022,2,11]]},"assertion":[{"value":"2022-02-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}