{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:04:22Z","timestamp":1784138662554,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809626","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"179-189","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Advantage-Conditioned Flow Policy for Offline Reinforcement Learning in 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, NSW, 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, NSW, 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":"The University of New South Wales, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=42zs3qa2kpy","author":"Chen Huayu","year":"2023","unstructured":"Huayu Chen, Cheng Lu, Chengyang Ying, Hang Su, and Jun Zhu. 2023a. Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=42zs3qa2kpy"},{"key":"e_1_3_2_1_2_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. 2021. Decision transformer: Reinforcement learning via sequence modeling. Advances in neural information processing systems, Vol. 34 (2021), 15084-15097."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729929"},{"key":"e_1_3_2_1_4_1","volume-title":"International conference on machine learning. PmLR, 1597-1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PmLR, 1597-1607."},{"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. 2023b. 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","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671750"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761076"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761336"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110335"},{"key":"e_1_3_2_1_10_1","volume-title":"A minimalist approach to offline reinforcement learning. Advances in neural information processing systems","author":"Fujimoto Scott","year":"2021","unstructured":"Scott Fujimoto and Shixiang Shane Gu. 2021. A minimalist approach to offline reinforcement learning. Advances in neural information processing systems, Vol. 34 (2021), 20132-20145."},{"key":"e_1_3_2_1_11_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_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557220"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557624"},{"key":"e_1_3_2_1_14_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_15_1","volume-title":"Jakub Grudzien Kuba, and Sergey Levine","author":"Hansen-Estruch Philippe","year":"2023","unstructured":"Philippe Hansen-Estruch, Ilya Kostrikov, Michael Janner, Jakub Grudzien Kuba, and Sergey Levine. 2023. Idql: Implicit q-learning as an actor-critic method with diffusion policies. arXiv preprint arXiv:2304.10573 (2023)."},{"key":"e_1_3_2_1_16_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_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657742"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/645531.656005"},{"key":"e_1_3_2_1_19_1","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar Aviral","year":"2020","unstructured":"Aviral Kumar, Aurick Zhou, George Tucker, and Sergey Levine. 2020. Conservative q-learning for offline reinforcement learning. Advances in Neural Information Processing Systems, Vol. 33 (2020), 1179-1191.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_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_21_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_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186150"},{"key":"e_1_3_2_1_23_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_24_1","volume-title":"Heli Ben-Hamu, Maximilian Nickel, and Matt Le.","author":"Lipman Yaron","year":"2022","unstructured":"Yaron Lipman, Ricky TQ Chen, Heli Ben-Hamu, Maximilian Nickel, and Matt Le. 2022. Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)."},{"key":"e_1_3_2_1_25_1","volume-title":"The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=XVjTT1nw5z","author":"Liu Xingchao","unstructured":"Xingchao Liu, Chengyue Gong, and qiang liu. 2023. Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=XVjTT1nw5z"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1639714.1639717"},{"key":"e_1_3_2_1_27_1","volume-title":"Flow Q-Learning. In Forty-second International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=KVf2SFL1pi","author":"Park Seohong","year":"2025","unstructured":"Seohong Park, Qiyang Li, and Sergey Levine. 2025. Flow Q-Learning. In Forty-second International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=KVf2SFL1pi"},{"key":"e_1_3_2_1_28_1","unstructured":"Xue Bin Peng Aviral Kumar Grace Zhang and Sergey Levine. 2021. Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning. https:\/\/openreview.net\/forum?id=ToWi1RjuEr8"},{"key":"e_1_3_2_1_29_1","first-page":"11702","article-title":"Bridging offline reinforcement learning and imitation learning: A tale of pessimism","volume":"34","author":"Rashidinejad Paria","year":"2021","unstructured":"Paria Rashidinejad, Banghua Zhu, Cong Ma, Jiantao Jiao, and Stuart Russell. 2021. Bridging offline reinforcement learning and imitation learning: A tale of pessimism. Advances in Neural Information Processing Systems, Vol. 34 (2021), 11702-11716.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_30_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_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"e_1_3_2_1_32_1","first-page":"32211","article-title":"Consistency Models","author":"Song Yang","year":"2023","unstructured":"Yang Song, Prafulla Dhariwal, Mark Chen, and Ilya Sutskever. 2023. Consistency Models. In ICML. 32211-32252. https:\/\/proceedings.mlr.press\/v202\/song23a.html","journal-title":"ICML."},{"key":"e_1_3_2_1_33_1","volume-title":"Conditional flow matching: Simulation-free dynamic optimal transport. arXiv preprint arXiv:2302.00482","author":"Tong Alexander","year":"2023","unstructured":"Alexander Tong, Nikolay Malkin, Guillaume Huguet, Yanlei Zhang, Jarrid Rector-Brooks, Kilian Fatras, Guy Wolf, and Yoshua Bengio. 2023. Conditional flow matching: Simulation-free dynamic optimal transport. arXiv preprint arXiv:2302.00482, Vol. 2, 3 (2023)."},{"key":"e_1_3_2_1_34_1","volume-title":"Behavioral cloning from observation. arXiv preprint arXiv:1805.01954","author":"Torabi Faraz","year":"2018","unstructured":"Faraz Torabi, Garrett Warnell, and Peter Stone. 2018. Behavioral cloning from observation. arXiv preprint arXiv:1805.01954 (2018)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591648"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679674"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714562"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3719208"},{"key":"e_1_3_2_1_39_1","volume-title":"The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=AHvFDPi-FA","author":"Wang Zhendong","year":"2023","unstructured":"Zhendong Wang, Jonathan J Hunt, and Mingyuan Zhou. 2023b. Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=AHvFDPi-FA"},{"key":"e_1_3_2_1_40_1","unstructured":"Yifan Wu George Tucker and Ofir Nachum. 2020. Behavior Regularized Offline Reinforcement Learning. https:\/\/openreview.net\/forum?id=BJg9hTNKPH"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1054"},{"key":"e_1_3_2_1_42_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_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3285029"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583418"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:10:07Z","timestamp":1784135407000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809626"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":46,"alternative-id":["10.1145\/3805712.3809626","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809626","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}