{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:26:16Z","timestamp":1783736776890,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671750","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:55:12Z","timestamp":1724561712000},"page":"376-384","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Maximum-Entropy Regularized Decision Transformer with Reward Relabelling for Dynamic 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":"The University of New South Wales, 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 & The University of New South Wales, Eveleigh, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_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_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018702"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186039"},{"key":"e_1_3_2_2_4_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_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474601"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207010"},{"key":"e_1_3_2_2_7_1","volume-title":"On the Opportunities and Challenges of Offline Reinforcement Learning for Recommender Systems. arXiv preprint arXiv:2308.11336","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. arXiv preprint arXiv:2308.11336 (2023)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532015"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110335"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482347"},{"key":"e_1_3_2_2_11_1","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_2_12_1","volume-title":"Alleviating matthew effect of offline reinforcement learning in interactive recommendation. arXiv preprint arXiv:2307.04571","author":"Gao Chongming","year":"2023","unstructured":"Chongming Gao, Kexin Huang, Jiawei Chen, Yuan Zhang, Biao Li, Peng Jiang, Shiqi Wang, Zhong Zhang, and Xiangnan He. 2023. Alleviating matthew effect of offline reinforcement learning in interactive recommendation. arXiv preprint arXiv:2307.04571 (2023)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557624"},{"key":"e_1_3_2_2_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_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219846"},{"key":"e_1_3_2_2_16_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_2_17_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_2_18_1","volume-title":"A survey on transformers in reinforcement learning. arXiv preprint arXiv:2301.03044","author":"Li Wenzhe","year":"2023","unstructured":"Wenzhe Li, Hao Luo, Zichuan Lin, Chongjie Zhang, Zongqing Lu, and Deheng Ye. 2023. A survey on transformers in reinforcement learning. arXiv preprint arXiv:2301.03044 (2023)."},{"key":"e_1_3_2_2_19_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_2_20_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_2_21_1","volume-title":"Awac: Accelerating online reinforcement learning with offline datasets. arXiv preprint arXiv:2006.09359","author":"Nair Ashvin","year":"2020","unstructured":"Ashvin Nair, Abhishek Gupta, Murtaza Dalal, and Sergey Levine. 2020. Awac: Accelerating online reinforcement learning with offline datasets. arXiv preprint arXiv:2006.09359 (2020)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240369"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591648"},{"key":"e_1_3_2_2_25_1","volume-title":"International Conference on Machine Learning. PMLR, 38989--39007","author":"Yamagata Taku","year":"2023","unstructured":"Taku Yamagata, Ahmed Khalil, and Raul Santos-Rodriguez. 2023. Q-learning decision transformer: Leveraging dynamic programming for conditional sequence modelling in offline rl. In International Conference on Machine Learning. PMLR, 38989--39007."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583418"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"},{"key":"e_1_3_2_2_29_1","volume-title":"international conference on machine learning. PMLR, 27042--27059","author":"Zheng Qinqing","year":"2022","unstructured":"Qinqing Zheng, Amy Zhang, and Aditya Grover. 2022. Online decision transformer. In international conference on machine learning. PMLR, 27042--27059."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1060745.1060754"}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671750","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:01Z","timestamp":1750291561000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671750"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":30,"alternative-id":["10.1145\/3637528.3671750","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671750","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}