{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T11:41:56Z","timestamp":1777030916079,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,7,25]],"date-time":"2019-07-25T00:00:00Z","timestamp":1564012800000},"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":[[2019,7,25]]},"DOI":"10.1145\/3292500.3330668","type":"proceedings-article","created":{"date-parts":[[2019,7,26]],"date-time":"2019-07-26T13:17:26Z","timestamp":1564147046000},"page":"2810-2818","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":201,"title":["Reinforcement Learning to Optimize Long-term User Engagement in Recommender Systems"],"prefix":"10.1145","author":[{"given":"Lixin","family":"Zou","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Long","family":"Xia","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}]},{"given":"Zhuoye","family":"Ding","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}]},{"given":"Jiaxing","family":"Song","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Weidong","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Dawei","family":"Yin","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2019,7,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2011.15"},{"key":"e_1_3_2_1_2_1","volume-title":"Optimal Greedy Diversity for Recommendation. In IJCAI'15","author":"Ashkan Azin","year":"2015"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052627"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052585"},{"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"},{"key":"e_1_3_2_1_6_1","volume-title":"More Robust Doubly Robust Off-policy Evaluation. In ICML'18","author":"Farajtabar Mehrdad","year":"2018"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159687"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330864"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_1_10_1","volume-title":"Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939","author":"Hidasi Bal\u00e1zs","year":"2015"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.2200\/S00605ED1V01Y201410ICR038"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132926"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_1_14_1","volume-title":"Partially Observable Markov Decision Process for Recommender Systems. arXiv preprint arXiv:1608.07793","author":"Lu Zhongqi","year":"2016"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1557914.1557930"},{"key":"e_1_3_2_1_16_1","volume-title":"Efficient Estimation of Word Representations in Vector Space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013"},{"key":"e_1_3_2_1_17_1","volume-title":"NIPS'08","author":"Mnih Andriy","year":"2008"},{"key":"e_1_3_2_1_18_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih Volodymyr","year":"2013"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020470"},{"key":"e_1_3_2_1_20_1","volume-title":"SDM'14","author":"Qin Lijing"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_1_22_1","volume-title":"ICML'16","author":"Schnabel Tobias","year":"2016"},{"key":"e_1_3_2_1_23_1","volume-title":"JMLR","volume":"6","author":"Shani Guy","year":"2005"},{"key":"e_1_3_2_1_24_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S"},{"key":"e_1_3_2_1_25_1","volume-title":"NIPS'15","author":"Swaminathan Adith","year":"2015"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298483.3298627"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159710"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3133025"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080775"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2645710.2645724"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939878"},{"key":"e_1_3_2_1_32_1","volume-title":"Deep Reinforcement Learning for Search, Recommendation, and Online Advertising: A Survey. arXiv preprint arXiv:1812.07127","author":"Zhao Xiangyu","year":"2018"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_1_35_1","volume-title":"Deep reinforcement learning for list-wise recommendations. arXiv preprint arXiv:1801.00209","author":"Zhao Xiangyu","year":"2017"},{"key":"e_1_3_2_1_36_1","volume-title":"ICML'16","author":"Zheng Yin","year":"2016"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159671"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172393"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-18579-4_7"}],"event":{"name":"KDD '19: The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Anchorage AK USA","acronym":"KDD '19","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3292500.3330668","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3292500.3330668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:02:09Z","timestamp":1750208529000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3292500.3330668"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,25]]},"references-count":39,"alternative-id":["10.1145\/3292500.3330668","10.1145\/3292500"],"URL":"https:\/\/doi.org\/10.1145\/3292500.3330668","relation":{},"subject":[],"published":{"date-parts":[[2019,7,25]]},"assertion":[{"value":"2019-07-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}