{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T04:07:01Z","timestamp":1783829221304,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"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":[[2024,10,21]]},"DOI":"10.1145\/3627673.3679674","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:21Z","timestamp":1729452861000},"page":"2390-2399","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["On Causally Disentangled State Representation Learning for Reinforcement Learning based Recommender Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8726-5277","authenticated-orcid":false,"given":"Siyu","family":"Wang","sequence":"first","affiliation":[{"name":"The University of New South Wales, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8849-4943","authenticated-orcid":false,"given":"Xiaocong","family":"Chen","sequence":"additional","affiliation":[{"name":"Data61,CSIRO, Eveleigh, 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":"Data61,CSIRO & The University of New South Wales, Eveleigh, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543846"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240360"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013312"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220122"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207010"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-023-01187-7"},{"key":"e_1_3_2_1_7_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_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110335"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482347"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3156066"},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning. PMLR, 1587--1596","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--1596."},{"key":"e_1_3_2_1_12_1","volume-title":"International Conference on Machine Learning. PMLR, 2170--2179","author":"Gelada Carles","year":"2019","unstructured":"Carles Gelada, Saurabh Kumar, Jacob Buckman, Ofir Nachum, and Marc G Bellemare. 2019. Deepmdp: Learning continuous latent space models for representation learning. In International Conference on Machine Learning. PMLR, 2170--2179."},{"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":"International Conference on Machine Learning. PMLR, 9260--9279","author":"Huang Biwei","year":"2022","unstructured":"Biwei Huang, Chaochao Lu, Liu Leqi, Jos\u00e9 Miguel Hern\u00e1ndez-Lobato, Clark Glymour, Bernhard Sch\u00f6lkopf, and Kun Zhang. 2022. Action-sufficient state representation learning for control with structural constraints. In International Conference on Machine Learning. PMLR, 9260--9279."},{"key":"e_1_3_2_1_15_1","volume-title":"Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning. In 7th International Conference on Learning Representations, ICLR 2019","author":"Kostrikov Ilya","year":"2019","unstructured":"Ilya Kostrikov, Kumar Krishna Agrawal, Debidatta Dwibedi, Sergey Levine, and Jonathan Tompson. 2019. Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6--9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=Hk4fpoA5Km"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"e_1_3_2_1_17_1","volume-title":"Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971","author":"Lillicrap Timothy P","year":"2015","unstructured":"Timothy P Lillicrap, Jonathan J 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_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401083"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106170"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5631"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1282100.1282114"},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Machine Learning. PMLR, 7502--7511","author":"Mastakouri Atalanti A","year":"2021","unstructured":"Atalanti A Mastakouri, Bernhard Sch\u00f6lkopf, and Dominik Janzing. 2021. Necessary and sufficient conditions for causal feature selection in time series with latent common causes. In International Conference on Machine Learning. PMLR, 7502--7511."},{"key":"e_1_3_2_1_23_1","unstructured":"Judea Pearl. 2009. Causality. Cambridge university press."},{"key":"e_1_3_2_1_24_1","volume-title":"Elements of Causal Inference: Foundations and Learning Algorithms","author":"Peters Jonas","unstructured":"Jonas Peters, Dominik Janzing, and Bernhard Schlkopf. 2017. Elements of Causal Inference: Foundations and Learning Algorithms. The MIT Press."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"e_1_3_2_1_26_1","volume-title":"prediction, and search","author":"Spirtes Peter","unstructured":"Peter Spirtes, Clark N Glymour, and Richard Scheines. 2000. Causation, prediction, and search. MIT press."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482420"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1599--1608","author":"Chen Xiaocong","year":"2023","unstructured":"SiyuWang, Xiaocong Chen, Dietmar Jannach, and Lina Yao. 2023. Causal decision transformer for recommender systems via offline reinforcement learning. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1599--1608."},{"key":"e_1_3_2_1_29_1","volume-title":"Plug-and-Play Model-Agnostic Counterfactual Policy Synthesis for Deep Reinforcement Learning-Based Recommendation","author":"Wang Siyu","year":"2023","unstructured":"Siyu Wang, Xiaocong Chen, Julian McAuley, Sally Cripps, and Lina Yao. 2023. Plug-and-Play Model-Agnostic Counterfactual Policy Synthesis for Deep Reinforcement Learning-Based Recommendation. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462962"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512251"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47426-3_8"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"23180","author":"Wang Zizhao","year":"2022","unstructured":"Zizhao Wang, Xuesu Xiao, Zifan Xu, Yuke Zhu, and Peter Stone. 2022. Causal Dynamics Learning for Task-Independent State Abstraction. In Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, 23151--23180. https: \/\/proceedings.mlr.press\/v162\/wang22ae.html"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331203"},{"key":"e_1_3_2_1_35_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=-2FCwDKRREu","author":"Zhang Amy","year":"2021","unstructured":"Amy Zhang, Rowan Thomas McAllister, Roberto Calandra, Yarin Gal, and Sergey Levine. 2021. Learning Invariant Representations for Reinforcement Learning without Reconstruction. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=-2FCwDKRREu"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462908"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462875"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679674","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3679674","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:13Z","timestamp":1750294693000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679674"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":38,"alternative-id":["10.1145\/3627673.3679674","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3679674","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}