{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:15:04Z","timestamp":1750220104698,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T00:00:00Z","timestamp":1657065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"A NeuralSymbolic Model for Knowledge Acquisition and Inference Techniques","award":["2020-0-00368"],"award-info":[{"award-number":["2020-0-00368"]}]},{"name":"Korea government (MSIT)","award":["2019-0-00075"],"award-info":[{"award-number":["2019-0-00075"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,6]]},"DOI":"10.1145\/3477495.3531869","type":"proceedings-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T15:12:13Z","timestamp":1657206733000},"page":"2607-2611","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Validating Long-Term User Feedbacks in Interactive Recommendation Systems"],"prefix":"10.1145","author":[{"given":"Hojoon","family":"Lee","sequence":"first","affiliation":[{"name":"KAIST, SeongNam, Republic of Korea"}]},{"given":"Dongyoon","family":"Hwang","sequence":"additional","affiliation":[{"name":"KAIST, SeongNam, Republic of Korea"}]},{"given":"Kyushik","family":"Min","sequence":"additional","affiliation":[{"name":"KAKAO Enterprise, SeongNam, Republic of Korea"}]},{"given":"Jaegul","family":"Choo","sequence":"additional","affiliation":[{"name":"KAIST, SeongNam, Republic of Korea"}]}],"member":"320","published-online":{"date-parts":[[2022,7,7]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013312"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3207"},{"key":"e_1_3_2_2_5_1","unstructured":"Yujing Hu Qing Da Anxiang Zeng Yang Yu and Yinghui Xu. 2018. Reinforce- ment Learning to Rank in E-Commerce Search Engine: Formalization Analysis and Application. In KDD.  Yujing Hu Qing Da Anxiang Zeng Yang Yu and Yinghui Xu. 2018. Reinforce- ment Learning to Rank in E-Commerce Search Engine: Formalization Analysis and Application. In KDD."},{"key":"e_1_3_2_2_6_1","volume-title":"Proc. the IEEE International Conference on Data Mining (ICDM). 197--206","author":"Kang Wang-Cheng","year":"2018","unstructured":"Wang-Cheng Kang and Julian McAuley . 2018 . Self-attentive sequential recom- mendation . In Proc. the IEEE International Conference on Data Mining (ICDM). 197--206 . Wang-Cheng Kang and Julian McAuley. 2018. Self-attentive sequential recom- mendation. In Proc. the IEEE International Conference on Data Mining (ICDM). 197--206."},{"key":"e_1_3_2_2_7_1","volume-title":"Matrix Factorization Tech- niques for Recommender Systems. Computer","author":"Koren Yehuda","year":"2009","unstructured":"Yehuda Koren , Robert Bell , and Chris Volinsky . 2009. Matrix Factorization Tech- niques for Recommender Systems. Computer ( 2009 ). Yehuda Koren, Robert Bell, and Chris Volinsky. 2009. Matrix Factorization Tech- niques for Recommender Systems. Computer (2009)."},{"key":"e_1_3_2_2_8_1","volume-title":"Schapire","author":"Li Lihong","year":"2010","unstructured":"Lihong Li , Wei Chu , John Langford , and Robert E . Schapire . 2010 . A Contextual- Bandit Approach to Personalized News Article Recommendation. In WWW. Lihong Li, Wei Chu, John Langford, and Robert E. Schapire. 2010. A Contextual- Bandit Approach to Personalized News Article Recommendation. In WWW."},{"key":"e_1_3_2_2_9_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 ). 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_2_10_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 ). 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_11_1","volume-title":"et al","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 (2015). 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 (2015)."},{"key":"e_1_3_2_2_12_1","unstructured":"Lijing Qin Shouyuan Chen and Xiaoyan Zhu. 2014. Contextual Combinatorial Bandit and its Application on Diversified Online Recommendation.  Lijing Qin Shouyuan Chen and Xiaoyan Zhu. 2014. Contextual Combinatorial Bandit and its Application on Diversified Online Recommendation."},{"volume-title":"Speech understanding systems: A summary of results of the five-year research effort","author":"Reddy Raj","key":"e_1_3_2_2_13_1","unstructured":"Raj Reddy . 1977. Speech understanding systems: A summary of results of the five-year research effort . In Carnegie Mellon University . Raj Reddy. 1977. Speech understanding systems: A summary of results of the five-year research effort. In Carnegie Mellon University."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372071"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_2_16_1","volume-title":"Proc. the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)","author":"Wang Fan","year":"2020","unstructured":"Fan Wang , Xiaomin Fang , Lihang Liu , Hao Tian , and Zhiming Peng . 2020 . MB- CAL: Sample Efficient and Variance Reduced Reinforcement Learning for Recom- mender Systems . Proc. the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) (2020). Fan Wang, Xiaomin Fang, Lihang Liu, Hao Tian, and Zhiming Peng. 2020. MB- CAL: Sample Efficient and Variance Reduced Reinforcement Learning for Recom- mender Systems. Proc. the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) (2020)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Huazheng Wang Qingyun Wu and Hongning Wang. 2017. Factorization Bandits for Interactive Recommendation. In AAAI.  Huazheng Wang Qingyun Wu and Hongning Wang. 2017. Factorization Bandits for Interactive Recommendation. In AAAI.","DOI":"10.1609\/aaai.v31i1.10936"},{"key":"e_1_3_2_2_18_1","unstructured":"Qingyun Wu Huazheng Wang Quanquan Gu and Hongning Wang. 2016. Con- textual Bandits in a Collaborative Environment. In SIGIR.  Qingyun Wu Huazheng Wang Quanquan Gu and Hongning Wang. 2016. Con- textual Bandits in a Collaborative Environment. In SIGIR."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401147"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_2_21_1","volume-title":"Proc. the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 1040--1048","author":"Zhao Xiangyu","year":"2018","unstructured":"Xiangyu Zhao , Liang Zhang , Zhuoye Ding , Long Xia , Jiliang Tang , and Dawei Yin . 2018 . Recommendations with negative feedback via pairwise deep reinforce- ment learning . In Proc. the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 1040--1048 . Xiangyu Zhao, Liang Zhang, Zhuoye Ding, Long Xia, Jiliang Tang, and Dawei Yin. 2018. Recommendations with negative feedback via pairwise deep reinforce- ment learning. In Proc. the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 1040--1048."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403384"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401174"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401181"}],"event":{"name":"SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Madrid Spain","acronym":"SIGIR '22"},"container-title":["Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531869","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477495.3531869","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:27Z","timestamp":1750183827000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531869"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":24,"alternative-id":["10.1145\/3477495.3531869","10.1145\/3477495"],"URL":"https:\/\/doi.org\/10.1145\/3477495.3531869","relation":{},"subject":[],"published":{"date-parts":[[2022,7,6]]},"assertion":[{"value":"2022-07-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}