{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T15:26:20Z","timestamp":1753889180443,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,9,13]],"date-time":"2022-09-13T00:00:00Z","timestamp":1663027200000},"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":[[2022,9,18]]},"DOI":"10.1145\/3523227.3551485","type":"proceedings-article","created":{"date-parts":[[2022,9,13]],"date-time":"2022-09-13T14:13:46Z","timestamp":1663078426000},"page":"622-627","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Multiobjective Evaluation of Reinforcement Learning Based Recommender Systems"],"prefix":"10.1145","author":[{"given":"Alexey","family":"Grishanov","sequence":"first","affiliation":[{"name":"Moscow Institute of Physics and Technology, Russian Federation and Sber AI Lab, Russian Federation"}]},{"given":"Anastasia","family":"Ianina","sequence":"additional","affiliation":[{"name":"Moscow Institute of Physics and Technology, Russian Federation"}]},{"given":"Konstantin","family":"Vorontsov","sequence":"additional","affiliation":[{"name":"Moscow Institute of Physics and Technology, Russian Federation"}]}],"member":"320","published-online":{"date-parts":[[2022,9,13]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"M\u00a0Mehdi Afsar Trafford Crump and Behrouz Far. 2021. Reinforcement learning based recommender systems: A survey. arXiv preprint arXiv:2101.06286(2021)."},{"key":"e_1_3_2_2_2_1","unstructured":"Lei\u00a0Jimmy Ba Jamie\u00a0Ryan Kiros and Geoffrey\u00a0E. Hinton. 2016. Layer Normalization. CoRR abs\/1607.06450(2016). arXiv:1607.06450http:\/\/arxiv.org\/abs\/1607.06450"},{"key":"e_1_3_2_2_3_1","volume-title":"A model-based reinforcement learning with adversarial training for online recommendation. Advances in Neural Information Processing Systems 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 32 (2019)."},{"key":"e_1_3_2_2_4_1","unstructured":"Gabriel Barth-Maron Matthew\u00a0W Hoffman David Budden Will Dabney Dan Horgan Dhruva Tb Alistair Muldal Nicolas Heess and Timothy Lillicrap. 2018. Distributed distributional deterministic policy gradients. arXiv preprint arXiv:1804.08617(2018)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242610"},{"key":"e_1_3_2_2_7_1","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:1512.07679\u00a0[cs.AI]"},{"key":"e_1_3_2_2_8_1","volume-title":"International conference on machine learning. PMLR, 1587\u20131596","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\u20131596."},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan","author":"Fujimoto Scott","year":"2018","unstructured":"Scott Fujimoto, Herke van Hoof, and David Meger. 2018. Addressing Function Approximation Error in Actor-Critic Methods. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10-15, 2018(Proceedings of Machine Learning Research, Vol.\u00a080), Jennifer\u00a0G. Dy and Andreas Krause (Eds.). PMLR, 1582\u20131591. http:\/\/proceedings.mlr.press\/v80\/fujimoto18a.html"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2827872"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412233"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"volume-title":"E-Commerce and Web Technologies","author":"Kompan Michal","key":"e_1_3_2_2_13_1","unstructured":"Michal Kompan and M\u00e1ria Bielikov\u00e1. 2010. Content-Based News Recommendation. In E-Commerce and Web Technologies, Francesco Buccafurri and Giovanni Semeraro (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 61\u201372."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_2_16_1","volume-title":"4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1509","author":"Lillicrap P.","year":"2016","unstructured":"Timothy\u00a0P. Lillicrap, Jonathan\u00a0J. Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. 2016. Continuous control with deep reinforcement learning. In 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1509.02971"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371858"},{"key":"e_1_3_2_2_18_1","unstructured":"Feng Liu Ruiming Tang Xutao Li Yunming Ye Haokun Chen Huifeng Guo and Yuzhou Zhang. 2018. Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling. ArXiv abs\/1810.12027(2018)."},{"key":"e_1_3_2_2_19_1","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_2_20_1","unstructured":"Zefang Liu Shuran Wen and Yinzhu Quan. 2021. Deep Reinforcement Learning based Group Recommender System. arXiv preprint arXiv:2106.06900(2021)."},{"key":"e_1_3_2_2_21_1","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_2_22_1","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2014.051006"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3190616"},{"key":"e_1_3_2_2_24_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arxiv:1707.06347\u00a0[cs.LG]"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3440207"},{"volume-title":"Collected works with commentaries","author":"Wiener Norbert","key":"e_1_3_2_2_27_1","unstructured":"Norbert Wiener. 1976. Collected works with commentaries. Mit Press."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16580"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10804"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3158369"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16156"},{"key":"e_1_3_2_2_32_1","volume-title":"Deep reinforcement learning for search, recommendation, and online advertising: a survey","author":"Zhao Xiangyu","year":"2019","unstructured":"Xiangyu Zhao, Long Xia, Jiliang Tang, and Dawei Yin. 2019. \u201d Deep reinforcement learning for search, recommendation, and online advertising: a survey\u201d by Xiangyu Zhao, Long Xia, Jiliang Tang, and Dawei Yin with Martin Vesely as coordinator. ACM sigweb newsletterSpring (2019), 1\u201315."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"crossref","unstructured":"Xiangyu Zhao Liang Zhang Zhuoye Ding Dawei Yin Yihong Zhao and Jiliang Tang. 2018. Deep Reinforcement Learning for List-wise Recommendations. ArXiv abs\/1801.00209(2018).","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"}],"event":{"name":"RecSys '22: Sixteenth 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"],"location":"Seattle WA USA","acronym":"RecSys '22"},"container-title":["Proceedings of the 16th ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3523227.3551485","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3523227.3551485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:09:29Z","timestamp":1750183769000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3523227.3551485"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,13]]},"references-count":36,"alternative-id":["10.1145\/3523227.3551485","10.1145\/3523227"],"URL":"https:\/\/doi.org\/10.1145\/3523227.3551485","relation":{},"subject":[],"published":{"date-parts":[[2022,9,13]]},"assertion":[{"value":"2022-09-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}