{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:41:27Z","timestamp":1780418487427,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":75,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"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":[[2025,4,22]]},"DOI":"10.1145\/3696410.3714807","type":"proceedings-article","created":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T16:42:02Z","timestamp":1746463322000},"page":"379-390","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Value Function Decomposition in Markov Recommendation Process"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7628-7257","authenticated-orcid":false,"given":"Xiaobei","family":"Wang","sequence":"first","affiliation":[{"name":"Kuaishou Technology, Beijing, 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, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6451-9299","authenticated-orcid":false,"given":"Qingpeng","family":"Cai","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6958-3388","authenticated-orcid":false,"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0697-8985","authenticated-orcid":false,"given":"Lantao","family":"Hu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9801-9292","authenticated-orcid":false,"given":"Han","family":"Li","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6504-0087","authenticated-orcid":false,"given":"Guangming","family":"Xie","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Reinforcement learning based recommender systems: A survey. ACM Computing Surveys (CSUR)","author":"Afsar M Mehdi","year":"2021","unstructured":"M Mehdi Afsar, Trafford Crump, and Behrouz Far. 2021. Reinforcement learning based recommender systems: A survey. ACM Computing Surveys (CSUR) (2021)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543846"},{"key":"e_1_3_2_1_3_1","volume-title":"Advances in Neural Information Processing Systems","volume":"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, Vol. 32 (2019)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0095693"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3584640"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583259"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599922"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013312"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441764"},{"key":"e_1_3_2_1_11_1","volume-title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model. CoRR abs\/2108.04468","author":"Chen Qiwei","year":"2021","unstructured":"Qiwei Chen, Changhua Pei, Shanshan Lv, Chao Li, Junfeng Ge, and Wenwu Ou. 2021b. End-to-End User Behavior Retrieval in Click-Through RatePrediction Model. CoRR abs\/2108.04468 (2021). arXiv preprint arXiv:2108.04468 (2021)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3661996"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482347"},{"key":"e_1_3_2_1_14_1","volume-title":"Deep reinforcement learning in large discrete action spaces. arXiv preprint arXiv:1512.07679","author":"Dulac-Arnold Gabriel","year":"2015","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 preprint arXiv:1512.07679 (2015)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186165"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557624"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441824"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498487"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583312"},{"key":"e_1_3_2_1_20_1","volume-title":"The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis) 5 4 (2015) 1--19","author":"Harper F Maxwell","year":"2015","unstructured":"F Maxwell Harper. 2015. The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis) 5 4 (2015) 1--19. F Maxwell Harper and Joseph A Konstan. 2015. The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis) 5 4 (2015) 1--19."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0030"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/360"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3109859.3109872"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108915"},{"key":"e_1_3_2_1_27_1","volume-title":"Actor-critic algorithms. Advances in neural information processing systems","author":"Konda Vijay","year":"1999","unstructured":"Vijay Konda and John Tsitsiklis. 1999. Actor-critic algorithms. Advances in neural information processing systems, Vol. 12 (1999)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_1_29_1","volume-title":"Advances in collaborative filtering. Recommender systems handbook","author":"Koren Yehuda","year":"2021","unstructured":"Yehuda Koren, Steffen Rendle, and Robert Bell. 2021. Advances in collaborative filtering. Recommender systems handbook (2021), 91--142."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the international AAAI conference on web and social media","volume":"7","author":"Lakkaraju Himabindu","year":"2013","unstructured":"Himabindu Lakkaraju, Julian McAuley, and Jure Leskovec. 2013. What's in a name? understanding the interplay between titles, content, and communities in social media. In Proceedings of the international AAAI conference on web and social media, Vol. 7. 311--320."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531941"},{"key":"e_1_3_2_1_32_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 Timothy P.","year":"2016","unstructured":"Timothy P. Lillicrap, Jonathan J. 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_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106170"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583244"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000016"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657829"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583467"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330984"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/1282100.1282114"},{"key":"e_1_3_2_1_40_1","unstructured":"Wenyu Mao Shuchang Liu Haoyang Liu Haozhe Liu Xiang Li and Lanatao Hu. 2025. Distinguished Quantized Guidance for Diffusion-based Sequence Recommendation. arxiv: 2501.17670 [cs.IR] https:\/\/arxiv.org\/abs\/2501.17670"},{"key":"e_1_3_2_1_41_1","volume-title":"Reinforced Prompt Personalization for Recommendation with Large Language Models. arXiv preprint arXiv:2407.17115","author":"Mao Wenyu","year":"2024","unstructured":"Wenyu Mao, Jiancan Wu, Weijian Chen, Chongming Gao, Xiang Wang, and Xiangnan He. 2024a. Reinforced Prompt Personalization for Recommendation with Large Language Models. arXiv preprint arXiv:2407.17115 (2024)."},{"key":"e_1_3_2_1_42_1","volume-title":"Invariant Graph Learning Meets Information Bottleneck for Out-of-Distribution Generalization. arXiv preprint arXiv:2408.01697","author":"Mao Wenyu","year":"2024","unstructured":"Wenyu Mao, Jiancan Wu, Haoyang Liu, Yongduo Sui, and Xiang Wang. 2024b. Invariant Graph Learning Meets Information Bottleneck for Out-of-Distribution Generalization. arXiv preprint arXiv:2408.01697 (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615004"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599838"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3606369"},{"key":"e_1_3_2_1_46_1","volume-title":"International conference on machine learning. PMLR","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous methods for deep reinforcement learning. In International conference on machine learning. PMLR, 1928--1937."},{"key":"e_1_3_2_1_47_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 et al. 2015. Human-level control through deep reinforcement learning. nature Vol. 518 7540 (2015) 529--533.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126314"},{"key":"e_1_3_2_1_49_1","first-page":"11767","article-title":"Softmax deep double deterministic policy gradients","volume":"33","author":"Pan Ling","year":"2020","unstructured":"Ling Pan, Qingpeng Cai, and Longbo Huang. 2020. Softmax deep double deterministic policy gradients. Advances in Neural Information Processing Systems, Vol. 33 (2020), 11767--11777.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313404"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412744"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772773"},{"key":"e_1_3_2_1_54_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_55_1","volume-title":"Policy learning for fairness in ranking. Advances in neural information processing systems","author":"Singh Ashudeep","year":"2019","unstructured":"Ashudeep Singh and Thorsten Joachims. 2019. Policy learning for fairness in ranking. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_57_1","volume-title":"Vinicius Zambaldi, Max Jaderberg, Marc Lanctot, Nicolas Sonnerat, Joel Z Leibo, Karl Tuyls, et al.","author":"Sunehag Peter","year":"2017","unstructured":"Peter Sunehag, Guy Lever, Audrunas Gruslys, Wojciech Marian Czarnecki, Vinicius Zambaldi, Max Jaderberg, Marc Lanctot, Nicolas Sonnerat, Joel Z Leibo, Karl Tuyls, et al. 2017. Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)."},{"key":"e_1_3_2_1_58_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S","unstructured":"Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/1297231.1297250"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412236"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671506"},{"key":"e_1_3_2_1_62_1","volume-title":"International conference on machine learning. PMLR","author":"Wang Ziyu","year":"2016","unstructured":"Ziyu Wang, Tom Schaul, Matteo Hessel, Hado Hasselt, Marc Lanctot, and Nando Freitas. 2016. Dueling network architectures for deep reinforcement learning. In International conference on machine learning. PMLR, 1995--2003."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080685"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331203"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401147"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531714"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599473"},{"key":"e_1_3_2_1_68_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_69_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Zhang Zeyu","year":"2024","unstructured":"Zeyu Zhang, Yi Su, Hui Yuan, Yiran Wu, Rishab Balasubramanian, Qingyun Wu, Huazheng Wang, and Mengdi Wang. 2024. Unified off-policy learning to rank: a reinforcement learning perspective. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_70_1","volume-title":"KuaiSim: A comprehensive simulator for recommender systems. arXiv preprint arXiv:2309.12645","author":"Zhao Kesen","year":"2023","unstructured":"Kesen Zhao, Shuchang Liu, Qingpeng Cai, Xiangyu Zhao, Ziru Liu, Dong Zheng, Peng Jiang, and Kun Gai. 2023. KuaiSim: A comprehensive simulator for recommender systems. arXiv preprint arXiv:2309.12645 (2023)."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16156"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412044"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-022-09413-y"}],"event":{"name":"WWW '25: The ACM Web Conference 2025","location":"Sydney NSW Australia","acronym":"WWW '25","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714807","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714807","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:42Z","timestamp":1750295922000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714807"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":75,"alternative-id":["10.1145\/3696410.3714807","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714807","relation":{},"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"2025-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}