{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:19:32Z","timestamp":1757312372610,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T00:00:00Z","timestamp":1694649600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,9,14]]},"DOI":"10.1145\/3604915.3608843","type":"proceedings-article","created":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T22:40:23Z","timestamp":1694731223000},"page":"877-882","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Scalable Deep Q-Learning for Session-Based Slate Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7085-3306","authenticated-orcid":false,"given":"Aayush","family":"Singha Roy","sequence":"first","affiliation":[{"name":"Computer Science, University College Dublin, Ireland and Insight Centre for Data Analytics,, Ireland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8262-7207","authenticated-orcid":false,"given":"Edoardo","family":"D'Amico","sequence":"additional","affiliation":[{"name":"Computer Science, University College Dublin, Ireland and Insight Centre for Data Analytics, Ireland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9566-531X","authenticated-orcid":false,"given":"Elias","family":"Tragos","sequence":"additional","affiliation":[{"name":"Computer Science, University College Dublin, Ireland and Insight Centre for Data Analytics, Ireland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6160-4639","authenticated-orcid":false,"given":"Aonghus","family":"Lawlor","sequence":"additional","affiliation":[{"name":"Computer Science, University College Dublin, Ireland and Insight Centre for Data Analytics, Ireland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8428-2866","authenticated-orcid":false,"given":"Neil","family":"Hurley","sequence":"additional","affiliation":[{"name":"Computer Science, University College Dublin, Ireland and Insight Centre for Data Analytics,, Ireland"}]}],"member":"320","published-online":{"date-parts":[[2023,9,14]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543846"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Machine Learning. PMLR, 1052\u20131061","author":"Chen Xinshi","year":"2019","unstructured":"Xinshi Chen, Shuang Li, Hui Li, Shaohua Jiang, Yuan Qi, and Le Song. 2019. Generative adversarial user model for reinforcement learning based recommendation system. In International Conference on Machine Learning. PMLR, 1052\u20131061."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Romain Deffayet Thibaut Thonet Jean-Michel Renders and Maarten de Rijke. 2023. Generative Slate Recommendation with Reinforcement Learning. (2023).","DOI":"10.1145\/3539597.3570412"},{"key":"e_1_3_2_1_5_1","volume-title":"Deep reinforcement learning in large discrete action spaces. arXiv preprint arXiv:1512.07679","author":"Dulac-Arnold Gabriel","year":"2015","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)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2843948"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330832"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3551468"},{"key":"e_1_3_2_1_9_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_10_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_11_1","volume-title":"Reinforcement learning for slate-based recommender systems: A tractable decomposition and practical methodology. arXiv preprint arXiv:1905.12767","author":"Ie Eugene","year":"2019","unstructured":"Eugene Ie, Vihan Jain, Jing Wang, Sanmit Narvekar, Ritesh Agarwal, Rui Wu, Heng-Tze Cheng, Morgane Lustman, Vince Gatto, Paul Covington, 2019. Reinforcement learning for slate-based recommender systems: A tractable decomposition and practical methodology. arXiv preprint arXiv:1905.12767 (2019)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/355102"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313613"},{"key":"e_1_3_2_1_14_1","volume-title":"Human-level control through deep reinforcement learning. nature 518, 7540","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei\u00a0A Rusu, Joel Veness, Marc\u00a0G Bellemare, Alex Graves, Martin Riedmiller, Andreas\u00a0K Fidjeland, Georg Ostrovski, 2015. Human-level control through deep reinforcement learning. nature 518, 7540 (2015), 529\u2013533."},{"key":"e_1_3_2_1_15_1","series-title":"SIAM journal on control and optimization 30, 4","volume-title":"Acceleration of stochastic approximation by averaging","author":"Polyak T","year":"1992","unstructured":"Boris\u00a0T Polyak and Anatoli\u00a0B Juditsky. 1992. Acceleration of stochastic approximation by averaging. SIAM journal on control and optimization 30, 4 (1992), 838\u2013855."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.32473\/flairs.36.133307"},{"key":"e_1_3_2_1_17_1","volume-title":"Off-policy evaluation for slate recommendation. Advances in Neural Information Processing Systems 30","author":"Swaminathan Adith","year":"2017","unstructured":"Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal, Miro Dudik, John Langford, Damien Jose, and Imed Zitouni. 2017. Off-policy evaluation for slate recommendation. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_1_18_1","volume-title":"Optimal bayesian recommendation sets and myopically optimal choice query sets. Advances in neural information processing systems 23","author":"Viappiani Paolo","year":"2010","unstructured":"Paolo Viappiani and Craig Boutilier. 2010. Optimal bayesian recommendation sets and myopically optimal choice query sets. Advances in neural information processing systems 23 (2010)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481899"}],"event":{"name":"RecSys '23: Seventeenth ACM Conference on Recommender Systems","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"],"location":"Singapore Singapore","acronym":"RecSys '23"},"container-title":["Proceedings of the 17th ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604915.3608843","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3604915.3608843","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:34Z","timestamp":1750178794000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604915.3608843"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,14]]},"references-count":19,"alternative-id":["10.1145\/3604915.3608843","10.1145\/3604915"],"URL":"https:\/\/doi.org\/10.1145\/3604915.3608843","relation":{},"subject":[],"published":{"date-parts":[[2023,9,14]]},"assertion":[{"value":"2023-09-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}