{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:26:19Z","timestamp":1783736779289,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761336","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:18:04Z","timestamp":1762561084000},"page":"332-341","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Maximum In-Support Return Modeling for Dynamic Recommendation with Language Model Prior"],"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","unstructured":"Michael Ahn Anthony Brohan Noah Brown Yevgen Chebotar Omar Cortes Byron David Chelsea Finn Chuyuan Fu Keerthana Gopalakrishnan Karol Hausman et al. 2022. Do as i can not as i say: Grounding language in robotic affordances. arXiv preprint arXiv:2204.01691 (2022)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608857"},{"key":"e_1_3_2_1_3_1","volume-title":"Jacob Portes, Mansheej Paul, Philip Greengard, Connor Jennings, Daniel King, Sam Havens, Vitaliy Chiley, Jonathan Frankle, et al.","author":"Biderman Dan","year":"2024","unstructured":"Dan Biderman, Jose Gonzalez Ortiz, Jacob Portes, Mansheej Paul, Philip Greengard, Connor Jennings, Daniel King, Sam Havens, Vitaliy Chiley, Jonathan Frankle, et al., 2024. Lora learns less and forgets less. arXiv preprint arXiv:2405.09673 (2024)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Anthony Brohan Noah Brown Justice Carbajal Yevgen Chebotar Joseph Dabis Chelsea Finn Keerthana Gopalakrishnan Karol Hausman Alex Herzog Jasmine Hsu et al. 2022. Rt-1: Robotics transformer for real-world control at scale. arXiv preprint arXiv:2212.06817 (2022).","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"e_1_3_2_1_5_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_6_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_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671750"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532015"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3186920"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28678"},{"key":"e_1_3_2_1_12_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_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557220"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557624"},{"key":"e_1_3_2_1_15_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_16_1","volume-title":"On pre-training for visuo-motor control: Revisiting a learning-from-scratch baseline. arXiv preprint arXiv:2212.05749","author":"Hansen Nicklas","year":"2022","unstructured":"Nicklas Hansen, Zhecheng Yuan, Yanjie Ze, Tongzhou Mu, Aravind Rajeswaran, Hao Su, Huazhe Xu, and Xiaolong Wang. 2022. On pre-training for visuo-motor control: Revisiting a learning-from-scratch baseline. arXiv preprint arXiv:2212.05749 (2022)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614949"},{"key":"e_1_3_2_1_18_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3648307"},{"key":"e_1_3_2_1_20_1","volume-title":"International conference on machine learning. PMLR, 9118-9147","author":"Huang Wenlong","year":"2022","unstructured":"Wenlong Huang, Pieter Abbeel, Deepak Pathak, and Igor Mordatch. 2022. Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. In International conference on machine learning. PMLR, 9118-9147."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1395-1406.","author":"Kim Sein","unstructured":"Sein Kim, Hongseok Kang, Seungyoon Choi, Donghyun Kim, Minchul Yang, and Chanyoung Park. 2024. Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1395-1406."},{"key":"e_1_3_2_1_22_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_23_1","first-page":"27921","article-title":"Multi-game decision transformers","volume":"35","author":"Lee Kuang-Huei","year":"2022","unstructured":"Kuang-Huei Lee, Ofir Nachum, Mengjiao Sherry Yang, Lisa Lee, Daniel Freeman, Sergio Guadarrama, Ian Fischer, Winnie Xu, Eric Jang, Henryk Michalewski, et al., 2022. Multi-game decision transformers. Advances in Neural Information Processing Systems, Vol. 35 (2022), 27921-27936.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_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_25_1","first-page":"31199","article-title":"Pre-trained language models for interactive decision-making","volume":"35","author":"Li Shuang","year":"2022","unstructured":"Shuang Li, Xavier Puig, Chris Paxton, Yilun Du, Clinton Wang, Linxi Fan, Tao Chen, De-An Huang, Ekin Aky\u00fcrek, Anima Anandkumar, et al., 2022. Pre-trained language models for interactive decision-making. Advances in Neural Information Processing Systems, Vol. 35 (2022), 31199-31212.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_26_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_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10131-7"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1639714.1639717"},{"key":"e_1_3_2_1_29_1","volume-title":"Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843","author":"Merity Stephen","year":"2016","unstructured":"Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. 2016. Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843 (2016)."},{"key":"e_1_3_2_1_30_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_31_1","volume-title":"Can wikipedia help offline reinforcement learning? arXiv preprint arXiv:2201.12122","author":"Reid Machel","year":"2022","unstructured":"Machel Reid, Yutaro Yamada, and Shixiang Shane Gu. 2022. Can wikipedia help offline reinforcement learning? arXiv preprint arXiv:2201.12122 (2022)."},{"key":"e_1_3_2_1_32_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_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"e_1_3_2_1_34_1","volume-title":"Unleashing the power of pre-trained language models for offline reinforcement learning. arXiv preprint arXiv:2310.20587","author":"Shi Ruizhe","year":"2023","unstructured":"Ruizhe Shi, Yuyao Liu, Yanjie Ze, Simon S Du, and Huazhe Xu. 2023. Unleashing the power of pre-trained language models for offline reinforcement learning. arXiv preprint arXiv:2310.20587 (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"A comparative study between full-parameter and lora-based fine-tuning on chinese instruction data for instruction following large language model. arXiv preprint arXiv:2304.08109","author":"Sun Xianghui","year":"2023","unstructured":"Xianghui Sun, Yunjie Ji, Baochang Ma, and Xiangang Li. 2023. A comparative study between full-parameter and lora-based fine-tuning on chinese instruction data for instruction following large language model. arXiv preprint arXiv:2304.08109 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"Saytap: Language to quadrupedal locomotion. arXiv preprint arXiv:2306.07580","author":"Tang Yujin","year":"2023","unstructured":"Yujin Tang, Wenhao Yu, Jie Tan, Heiga Zen, Aleksandra Faust, and Tatsuya Harada. 2023. Saytap: Language to quadrupedal locomotion. arXiv preprint arXiv:2306.07580 (2023)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591648"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714562"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3719208"},{"key":"e_1_3_2_1_40_1","volume-title":"Prompt a robot to walk with large language models. arXiv preprint arXiv:2309.09969","author":"Wang Yen-Jen","year":"2023","unstructured":"Yen-Jen Wang, Bike Zhang, Jianyu Chen, and Koushil Sreenath. 2023b. Prompt a robot to walk with large language models. arXiv preprint arXiv:2309.09969 (2023)."},{"key":"e_1_3_2_1_41_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_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3259681"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608885"},{"key":"e_1_3_2_1_44_1","volume-title":"DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Reward. arXiv preprint arXiv:2505.07257","author":"Zhang Yi","year":"2025","unstructured":"Yi Zhang, Ruihong Qiu, Xuwei Xu, Jiajun Liu, and Sen Wang. 2025. DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Reward. arXiv preprint arXiv:2505.07257 (2025)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583418"}],"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\/3746252.3761336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:39:00Z","timestamp":1765503540000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761336"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":45,"alternative-id":["10.1145\/3746252.3761336","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761336","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"}}]}}