{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T04:30:01Z","timestamp":1769574601536,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":51,"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"}],"funder":[{"name":"APRC - CityU New Research Initiatives","award":["No.9610565"],"award-info":[{"award-number":["No.9610565"]}]},{"name":"HKIDS Early Career Research Grant","award":["No.9360163"],"award-info":[{"award-number":["No.9360163"]}]},{"name":"Huawei Innovation Research Program"},{"name":"SIRG - CityU Strategic Interdisciplinary Research Grant","award":["No.7020046, No.7020074"],"award-info":[{"award-number":["No.7020046, No.7020074"]}]},{"name":"Ant Group (CCF-Ant Research Fund)"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543507.3583418","type":"proceedings-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T23:30:25Z","timestamp":1682551825000},"page":"1141-1149","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["User Retention-oriented Recommendation with Decision Transformer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7187-3381","authenticated-orcid":false,"given":"Kesen","family":"Zhao","sequence":"first","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6755-871X","authenticated-orcid":false,"given":"Lixin","family":"Zou","sequence":"additional","affiliation":[{"name":"Wuhan University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2926-4416","authenticated-orcid":false,"given":"Xiangyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0073-0172","authenticated-orcid":false,"given":"Maolin","family":"Wang","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8846-2001","authenticated-orcid":false,"given":"Dawei","family":"Yin","sequence":"additional","affiliation":[{"name":"Baidu Inc., China"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013312"},{"key":"e_1_3_2_1_2_1","volume-title":"Decision transformer: Reinforcement learning via sequence modeling. Advances in neural information processing systems 34","author":"Chen Lili","year":"2021","unstructured":"Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Misha Laskin, Pieter Abbeel, Aravind Srinivas, and Igor Mordatch. 2021. Decision transformer: Reinforcement learning via sequence modeling. Advances in neural information processing systems 34 (2021), 15084\u201315097."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441764"},{"key":"e_1_3_2_1_5_1","volume-title":"International Conference on Machine Learning. PMLR, 1052\u20131061","author":"Chen Xinshi","year":"2019","unstructured":"Xinshi Chen, Shuang Li, Hui Li, Shaohua Jiang, Yuan Qi, and Le Song. 2019. Generative adversarial user model for reinforcement learning based recommendation system. In International Conference on Machine Learning. PMLR, 1052\u20131061."},{"key":"e_1_3_2_1_6_1","volume-title":"A survey of deep reinforcement learning in recommender systems: A systematic review and future directions. arXiv preprint arXiv:2109.03540","author":"Chen Xiaocong","year":"2021","unstructured":"Xiaocong Chen, Lina Yao, Julian McAuley, Guanglin Zhou, and Xianzhi Wang. 2021. A survey of deep reinforcement learning in recommender systems: A systematic review and future directions. arXiv preprint arXiv:2109.03540 (2021)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242610"},{"key":"e_1_3_2_1_9_1","volume-title":"Time-sensitive recommendation from recurrent user activities. Advances in neural information processing systems 28","author":"Du Nan","year":"2015","unstructured":"Nan Du, Yichen Wang, Niao He, Jimeng Sun, and Le Song. 2015. Time-sensitive recommendation from recurrent user activities. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 315\u2013323","author":"Glorot Xavier","year":"2011","unstructured":"Xavier Glorot, Antoine Bordes, and Yoshua Bengio. 2011. Deep sparse rectifier neural networks. In Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 315\u2013323."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_13_1","volume-title":"Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)."},{"key":"e_1_3_2_1_14_1","volume-title":"Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939","author":"Hidasi Bal\u00e1zs","year":"2015","unstructured":"Bal\u00e1zs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2015. Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939 (2015)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959167"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2792838.2799684"},{"key":"e_1_3_2_1_17_1","unstructured":"Eugene Ie Vihan Jain Jing Wang Sanmit Narvekar Ritesh Agarwal Rui Wu Heng-Tze Cheng Tushar Chandra and Craig Boutilier. 2019. SlateQ: A tractable decomposition for reinforcement learning with recommendation sets. (2019)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of NAACL-HLT. 4171\u20134186","author":"Ming-Wei\u00a0Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei\u00a0Chang Kenton and Lee\u00a0Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT. 4171\u20134186."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.08.271"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/297"},{"key":"e_1_3_2_1_23_1","volume-title":"Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74\u201381.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74\u201381."},{"key":"e_1_3_2_1_24_1","volume-title":"A survey on reinforcement learning for recommender systems. arXiv preprint arXiv:2109.10665","author":"Lin Yuanguo","year":"2021","unstructured":"Yuanguo Lin, Yong Liu, Fan Lin, Pengcheng Wu, Wenhua Zeng, and Chunyan Miao. 2021. A survey on reinforcement learning for recommender systems. arXiv preprint arXiv:2109.10665 (2021)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401099"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311\u2013318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311\u2013318."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772773"},{"key":"e_1_3_2_1_29_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_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_31_1","volume-title":"Sequence to sequence learning with neural networks. Advances in neural information processing systems 27","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc\u00a0V Le. 2014. Sequence to sequence learning with neural networks. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988452"},{"key":"e_1_3_2_1_33_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 26th annual conference on learning theory (COLT","author":"Wang Yining","year":"2013","unstructured":"Yining Wang, Liwei Wang, Yuanzhi Li, Di He, Wei Chen, and Tie-Yan Liu. 2013. A theoretical analysis of NDCG ranking measures. In Proceedings of the 26th annual conference on learning theory (COLT 2013), Vol.\u00a08. 6."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3133025"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531714"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2645710.2645724"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557348"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401467"},{"key":"e_1_3_2_1_40_1","volume-title":"Deep reinforcement learning for search, recommendation, and online advertising: a survey. ACM SIGWEB NewsletterSpring","author":"Zhao Xiangyu","year":"2019","unstructured":"Xiangyu Zhao, Long Xia, Jiliang Tang, and Dawei Yin. 2019. Deep reinforcement learning for search, recommendation, and online advertising: a survey. ACM SIGWEB NewsletterSpring (2019), 1\u201315."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_1_42_1","volume-title":"Whole-Chain Recommendations. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 1883\u20131891","author":"Zhao Xiangyu","year":"2020","unstructured":"Xiangyu Zhao, Long Xia, Lixin Zou, Hui Liu, Dawei Yin, and Jiliang Tang. 2020. Whole-Chain Recommendations. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 1883\u20131891."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450125"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_1_45_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, Zhuoye Ding, Dawei Yin, Yihong Zhao, and Jiliang Tang. 2017. Deep Reinforcement Learning for List-wise Recommendations. arXiv preprint arXiv:1801.00209 (2017)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568681"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330668"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371801"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401181"},{"key":"e_1_3_2_1_50_1","volume-title":"Data-Efficient Reinforcement Learning for Malaria Control. arXiv e-prints","author":"Zou Lixin","year":"2021","unstructured":"Lixin Zou, Long Xia, Linfang Hou, Xiangyu Zhao, and Dawei Yin. 2021. Data-Efficient Reinforcement Learning for Malaria Control. arXiv e-prints (2021), arXiv\u20132105."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467147"}],"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":["Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583418","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583418","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:52Z","timestamp":1750178872000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583418"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":51,"alternative-id":["10.1145\/3543507.3583418","10.1145\/3543507"],"URL":"https:\/\/doi.org\/10.1145\/3543507.3583418","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"}}]}}