{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:45:54Z","timestamp":1787017554029,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761076","type":"proceedings-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T18:37:32Z","timestamp":1762799852000},"page":"322-331","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Energy-Guided Diffusion Sampling for Long-Term User Behavior Prediction in Reinforcement Learning-based Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8849-4943","authenticated-orcid":false,"given":"Xiaocong","family":"Chen","sequence":"first","affiliation":[{"name":"Data 61, CSIRO, Eveleigh, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8726-5277","authenticated-orcid":false,"given":"Siyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Macquarie University, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4149-839X","authenticated-orcid":false,"given":"Lina","family":"Yao","sequence":"additional","affiliation":[{"name":"Data 61, CSIRO, Eveleigh, Australia and The University of New South Wales, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018702"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186039"},{"key":"e_1_3_2_1_3_1","volume-title":"Decision transformer: Reinforcement learning via sequence modeling. Advances in neural information processing systems","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. 2021a. Decision transformer: Reinforcement learning via sequence modeling. Advances in neural information processing systems, Vol. 34 (2021), 15084-15097."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207010"},{"key":"e_1_3_2_1_5_1","volume-title":"On the opportunities and challenges of offline reinforcement learning for recommender systems. ACM Transactions on Information Systems","author":"Chen Xiaocong","year":"2023","unstructured":"Xiaocong Chen, Siyu Wang, Julian McAuley, Dietmar Jannach, and Lina Yao. 2023a. On the opportunities and challenges of offline reinforcement learning for recommender systems. ACM Transactions on Information Systems (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"Maximum-Entropy Regularized Decision Transformer with Reward Relabelling for Dynamic Recommendation. arXiv preprint arXiv:2406.00725","author":"Chen Xiaocong","year":"2024","unstructured":"Xiaocong Chen, Siyu Wang, and Lina Yao. 2024. Maximum-Entropy Regularized Decision Transformer with Reward Relabelling for Dynamic Recommendation. arXiv preprint arXiv:2406.00725 (2024)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110335"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482347"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3186920"},{"key":"e_1_3_2_1_10_1","first-page":"1582","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan","author":"Fujimoto Scott","year":"2018","unstructured":"Scott Fujimoto, Herke van Hoof, and David Meger. 2018. Addressing Function Approximation Error in Actor-Critic Methods. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10-15, 2018 (Proceedings of Machine Learning Research, Vol. 80). PMLR, 1582-1591. http:\/\/proceedings.mlr.press\/v80\/fujimoto18a.html"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557220"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557624"},{"key":"e_1_3_2_1_13_1","volume-title":"International conference on machine learning. PMLR","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning. PMLR, 1861-1870."},{"key":"e_1_3_2_1_14_1","volume-title":"Diffusion model is an effective planner and data synthesizer for multi-task reinforcement learning. Advances in neural information processing systems","author":"He Haoran","year":"2024","unstructured":"Haoran He, Chenjia Bai, Kang Xu, Zhuoran Yang, Weinan Zhang, Dong Wang, Bin Zhao, and Xuelong Li. 2024. Diffusion model is an effective planner and data synthesizer for multi-task reinforcement learning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840-6851."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219846"},{"key":"e_1_3_2_1_17_1","volume-title":"Offline reinforcement learning with implicit q-learning. arXiv preprint arXiv:2110.06169","author":"Kostrikov Ilya","year":"2021","unstructured":"Ilya Kostrikov, Ashvin Nair, and Sergey Levine. 2021. Offline reinforcement learning with implicit q-learning. arXiv preprint arXiv:2110.06169 (2021)."},{"key":"e_1_3_2_1_18_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_19_1","first-page":"1","article-title":"Diffurec: A diffusion model for sequential recommendation","volume":"42","author":"Li Zihao","year":"2023","unstructured":"Zihao Li, Aixin Sun, and Chenliang Li. 2023. Diffurec: A diffusion model for sequential recommendation. ACM Transactions on Information Systems, Vol. 42, 3 (2023), 1-28.","journal-title":"ACM Transactions on Information Systems"},{"key":"e_1_3_2_1_20_1","volume-title":"4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings. 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. http:\/\/arxiv.org\/abs\/1509.02971"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615134"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28736"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1639714.1639717"},{"key":"e_1_3_2_1_24_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)."},{"key":"e_1_3_2_1_25_1","volume-title":"Shan Zheng Tan, Ida Momennejad, Katja Hofmann, et al.","author":"Pearce Tim","year":"2023","unstructured":"Tim Pearce, Tabish Rashid, Anssi Kanervisto, Dave Bignell, Mingfei Sun, Raluca Georgescu, Sergio Valcarcel Macua, Shan Zheng Tan, Ida Momennejad, Katja Hofmann, et al., 2023. Imitating human behaviour with diffusion models. arXiv preprint arXiv:2301.10677 (2023)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_27_1","volume-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning. arXiv preprint arXiv:1910.00177","author":"Peng Xue Bin","year":"2019","unstructured":"Xue Bin Peng, Aviral Kumar, Grace Zhang, and Sergey Levine. 2019. Advantage-weighted regression: Simple and scalable off-policy reinforcement learning. arXiv preprint arXiv:1910.00177 (2019)."},{"key":"e_1_3_2_1_28_1","first-page":"1","article-title":"A diffusion model for poi recommendation","volume":"42","author":"Qin Yifang","year":"2023","unstructured":"Yifang Qin, Hongjun Wu, Wei Ju, Xiao Luo, and Ming Zhang. 2023. A diffusion model for poi recommendation. ACM Transactions on Information Systems, Vol. 42, 2 (2023), 1-27.","journal-title":"ACM Transactions on Information Systems"},{"key":"e_1_3_2_1_29_1","volume-title":"international conference on machine learning. PMLR, 1670-1679","author":"Schnabel Tobias","year":"2016","unstructured":"Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak, and Thorsten Joachims. 2016. Recommendations as treatments: Debiasing learning and evaluation. In international conference on machine learning. PMLR, 1670-1679."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"e_1_3_2_1_31_1","volume-title":"Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456","author":"Song Yang","year":"2020","unstructured":"Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2020. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591648"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714562"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3719208"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Yuanqing Yu Chongming Gao Jiawei Chen Heng Tang Yuefeng Sun Qian Chen Weizhi Ma and Min Zhang. 2024. EasyRL4Rec: A User-Friendly Code Library for Reinforcement Learning Based Recommender Systems. arXiv:2402.15164 [cs.IR]","DOI":"10.1145\/3626772.3657868"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583418"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"},{"key":"e_1_3_2_1_39_1","volume-title":"Diffusion models for reinforcement learning: A survey. arXiv preprint arXiv:2311.01223","author":"Zhu Zhengbang","year":"2023","unstructured":"Zhengbang Zhu, Hanye Zhao, Haoran He, Yichao Zhong, Shenyu Zhang, Haoquan Guo, Tingting Chen, and Weinan Zhang. 2023. Diffusion models for reinforcement learning: A survey. arXiv preprint arXiv:2311.01223 (2023)."}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761076","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:43:06Z","timestamp":1765500186000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761076"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":39,"alternative-id":["10.1145\/3746252.3761076","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761076","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}