{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T05:20:48Z","timestamp":1784784048887,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"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":[[2023,4,30]]},"DOI":"10.1145\/3543873.3584640","type":"proceedings-article","created":{"date-parts":[[2023,4,28]],"date-time":"2023-04-28T11:36:14Z","timestamp":1682681774000},"page":"421-426","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":37,"title":["Reinforcing User Retention in a Billion Scale Short Video Recommender System"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6451-9299","authenticated-orcid":false,"given":"Qingpeng","family":"Cai","sequence":"first","affiliation":[{"name":"Kuaishou Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1440-911X","authenticated-orcid":false,"given":"Shuchang","family":"Liu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5935-3757","authenticated-orcid":false,"given":"Xueliang","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2733-1235","authenticated-orcid":false,"given":"Tianyou","family":"Zuo","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6733-2291","authenticated-orcid":false,"given":"Wentao","family":"Xie","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7899-2017","authenticated-orcid":false,"given":"Bin","family":"Yang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0424-9658","authenticated-orcid":false,"given":"Dong","family":"Zheng","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9266-0780","authenticated-orcid":false,"given":"Peng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3636-3618","authenticated-orcid":false,"given":"Kun","family":"Gai","sequence":"additional","affiliation":[{"name":"Unaffiliated, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Reinforcement learning based recommender systems: A survey. arXiv preprint arXiv:2101.06286","author":"Afsar M\u00a0Mehdi","year":"2021","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_1_2_1","volume-title":"Exploration by random network distillation. arXiv preprint arXiv:1810.12894","author":"Burda Yuri","year":"2018","unstructured":"Yuri Burda, Harrison Edwards, Amos Storkey, and Oleg Klimov. 2018. Exploration by random network distillation. arXiv preprint arXiv:1810.12894 (2018)."},{"key":"e_1_3_2_1_3_1","volume-title":"Two-Stage Constrained Actor-Critic fo Short Video Recommendation. arXiv preprint arXiv:2302.01680","author":"Cai Qingpeng","year":"2023","unstructured":"Qingpeng Cai, Zhenghai Xue, Chi Zhang, Wanqi Xue, Shuchang Liu, Ruohan Zhan, Xueliang Wang, Tianyou Zuo, Wentao Xie, Dong Zheng, 2023. Two-Stage Constrained Actor-Critic fo Short Video Recommendation. arXiv preprint arXiv:2302.01680 (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013312"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220122"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_7_1","volume-title":"A minimalist approach to offline reinforcement learning. Advances in neural information processing systems 34","author":"Fujimoto Scott","year":"2021","unstructured":"Scott Fujimoto and Shixiang\u00a0Shane Gu. 2021. A minimalist approach to offline reinforcement learning. Advances in neural information processing systems 34 (2021), 20132\u201320145."},{"key":"e_1_3_2_1_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_1_9_1","volume-title":"CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender System. arXiv preprint arXiv:2204.01266","author":"Gao Chongming","year":"2022","unstructured":"Chongming Gao, Wenqiang Lei, Jiawei Chen, Shiqi Wang, Xiangnan He, Shijun Li, Biao Li, Yuan Zhang, and Peng Jiang. 2022. CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender System. arXiv preprint arXiv:2204.01266 (2022)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557624"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441824"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557065"},{"key":"e_1_3_2_1_13_1","unstructured":"Marek Grzes. 2017. Reward shaping in episodic reinforcement learning. (2017)."},{"key":"e_1_3_2_1_14_1","volume-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643","author":"Levine Sergey","year":"2020","unstructured":"Sergey Levine, Aviral Kumar, George Tucker, and Justin Fu. 2020. Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643 (2020)."},{"key":"e_1_3_2_1_15_1","volume-title":"Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971","author":"Lillicrap P","year":"2015","unstructured":"Timothy\u00a0P Lillicrap, Jonathan\u00a0J 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_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539130"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2925019"},{"key":"e_1_3_2_1_18_1","volume-title":"Exploration and Regularization of the Latent Action Space in Recommendation. arXiv preprint arXiv:2302.03431","author":"Liu Shuchang","year":"2023","unstructured":"Shuchang Liu, Qingpeng Cai, Bowen Sun, Yuhao Wang, Ji Jiang, Dong Zheng, Kun Gai, Peng Jiang, Xiangyu Zhao, and Yongfeng Zhang. 2023. Exploration and Regularization of the Latent Action Space in Recommendation. arXiv preprint arXiv:2302.03431 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Multi-Task Recommendations with Reinforcement Learning. arXiv preprint arXiv:2302.03328","author":"Liu Ziru","year":"2023","unstructured":"Ziru Liu, Jiejie Tian, Qingpeng Cai, Xiangyu Zhao, Jingtong Gao, Shuchang Liu, Dayou Chen, Tonghao He, Dong Zheng, Peng Jiang, 2023. Multi-Task Recommendations with Reinforcement Learning. arXiv preprint arXiv:2302.03328 (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380130"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2016.7591355"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347000"},{"key":"e_1_3_2_1_24_1","volume-title":"Monte-Carlo simulation, and machine learning. Vol.\u00a0133","author":"Rubinstein Y","unstructured":"Reuven\u00a0Y Rubinstein and Dirk\u00a0P Kroese. 2004. The cross-entropy method: a unified approach to combinatorial optimization, Monte-Carlo simulation, and machine learning. Vol.\u00a0133. Springer."},{"key":"e_1_3_2_1_25_1","volume-title":"Julian Schrittwieser, Ioannis Antonoglou","author":"Silver David","year":"2016","unstructured":"David Silver, Aja Huang, Chris\u00a0J Maddison, Arthur Guez, Laurent Sifre, George Van Den\u00a0Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, 2016. Mastering the game of Go with deep neural networks and tree search. nature 529, 7587 (2016), 484\u2013489."},{"key":"e_1_3_2_1_26_1","unstructured":"Richard\u00a0S Sutton Andrew\u00a0G Barto 1998. Introduction to reinforcement learning. (1998)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539354"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539073"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9045(74)90012-4"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3133025"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331203"},{"key":"e_1_3_2_1_32_1","volume-title":"ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor. arXiv preprint arXiv:2206.02620","author":"Xue Wanqi","year":"2022","unstructured":"Wanqi Xue, Qingpeng Cai, Ruohan Zhan, Dong Zheng, Peng Jiang, and Bo An. 2022. ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor. arXiv preprint arXiv:2206.02620 (2022)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539092"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539040"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_1_36_1","volume-title":"Deep reinforcement learning for list-wise recommendations. arXiv preprint arXiv:1801.00209","author":"Zhao Xiangyu","year":"2017","unstructured":"Xiangyu Zhao, Liang Zhang, Long Xia, Zhuoye Ding, Dawei Yin, and Jiliang Tang. 2017. Deep reinforcement learning for list-wise recommendations. arXiv preprint arXiv:1801.00209 (2017)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330668"}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543873.3584640","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543873.3584640","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:30:41Z","timestamp":1755819041000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543873.3584640"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":37,"alternative-id":["10.1145\/3543873.3584640","10.1145\/3543873"],"URL":"https:\/\/doi.org\/10.1145\/3543873.3584640","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}