{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T21:39:43Z","timestamp":1768426783423,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":21,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,6]]},"DOI":"10.1145\/3477495.3531847","type":"proceedings-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T15:12:13Z","timestamp":1657206733000},"page":"2292-2296","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Deep Page-Level Interest Network in Reinforcement Learning for Ads Allocation"],"prefix":"10.1145","author":[{"given":"Guogang","family":"Liao","sequence":"first","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowen","family":"Shi","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ze","family":"Wang","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoxu","family":"Wu","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongkang","family":"Wang","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingxing","family":"Wang","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,7,7]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"Zhifang Fan Dan Ou Yulong Gu Bairan Fu Xiang Li Wentian Bao Xin-Yu Dai Xiaoyi Zeng Tao Zhuang and Qingwen Liu. 2022. Modeling Users' Contextualized Page-wise Feedback for Click-Through Rate Prediction in E-commerce Search. (2022).  Zhifang Fan Dan Ou Yulong Gu Bairan Fu Xiang Li Wentian Bao Xin-Yu Dai Xiaoyi Zeng Tao Zhuang and Qingwen Liu. 2022. Modeling Users' Contextualized Page-wise Feedback for Click-Through Rate Prediction in E-commerce Search. (2022).","DOI":"10.1145\/3488560.3498478"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186165"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1090.1054"},{"key":"e_1_3_2_2_4_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). 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_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411952"},{"key":"e_1_3_2_2_6_1","volume-title":"Cross DQN: Cross Deep Q Network for Ads Allocation in Feed. arXiv preprint arXiv:2109.04353","author":"Liao Guogang","year":"2021","unstructured":"Guogang Liao , Ze Wang , Xiaoxu Wu , Xiaowen Shi , Chuheng Zhang , Yongkang Wang , Xingxing Wang , and Dong Wang . 2021. Cross DQN: Cross Deep Q Network for Ads Allocation in Feed. arXiv preprint arXiv:2109.04353 ( 2021 ). Guogang Liao, Ze Wang, Xiaoxu Wu, Xiaowen Shi, Chuheng Zhang, Yongkang Wang, Xingxing Wang, and Dong Wang. 2021. Cross DQN: Cross Deep Q Network for Ads Allocation in Feed. arXiv preprint arXiv:2109.04353 (2021)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1561\/0400000057"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"crossref","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei A Rusu Joel Veness Marc G Bellemare Alex Graves Martin Riedmiller Andreas K Fidjeland Georg Ostrovski etal 2015. Human-level control through deep reinforcement learning. nature 518 7540 (2015) 529--533.  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 518 7540 (2015) 529--533.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330666"},{"key":"e_1_3_2_2_10_1","unstructured":"Richard S Sutton Andrew G Barto etal 1998. Introduction to reinforcement learning. Vol. 135. MIT press Cambridge.  Richard S Sutton Andrew G Barto et al. 1998. Introduction to reinforcement learning. Vol. 135. MIT press Cambridge."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"B. Wang Zhaonan Li Jie Tang Kuo Zhang Songcan Chen and Liyun Ru. 2011. Learning to Advertise: How Many Ads Are Enough?. In PAKDD.  B. Wang Zhaonan Li Jie Tang Kuo Zhang Songcan Chen and Liyun Ru. 2011. Learning to Advertise: How Many Ads Are Enough?. In PAKDD.","DOI":"10.1007\/978-3-642-20847-8_42"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412092"},{"key":"e_1_3_2_2_13_1","volume-title":"Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence. 2519--2525","author":"Xie Ruobing","year":"2021","unstructured":"Ruobing Xie , Cheng Ling , Yalong Wang , Rui Wang , Feng Xia , and Leyu Lin . 2021 . Deep feedback network for recommendation . In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence. 2519--2525 . Ruobing Xie, Cheng Ling, Yalong Wang, Rui Wang, Feng Xia, and Leyu Lin. 2021. Deep feedback network for recommendation. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence. 2519--2525."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16580"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403391"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3191584"},{"key":"e_1_3_2_2_17_1","volume-title":"A Non-sequential Approach to Deep User Interest Model for CTR Prediction. arXiv preprint arXiv:2104.06312","author":"Zhao Keke","year":"2021","unstructured":"Keke Zhao , Xing Zhao , Qi Cao , and Linjian Mo. 2021. A Non-sequential Approach to Deep User Interest Model for CTR Prediction. arXiv preprint arXiv:2104.06312 ( 2021 ). Keke Zhao, Xing Zhao, Qi Cao, and Linjian Mo. 2021. A Non-sequential Approach to Deep User Interest Model for CTR Prediction. arXiv preprint arXiv:2104.06312 (2021)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16156"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403384"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015941"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"}],"event":{"name":"SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Madrid Spain","acronym":"SIGIR '22","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"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\/3477495.3531847","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477495.3531847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:26Z","timestamp":1750183826000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531847"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":21,"alternative-id":["10.1145\/3477495.3531847","10.1145\/3477495"],"URL":"https:\/\/doi.org\/10.1145\/3477495.3531847","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"}}]}}