{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T15:25:33Z","timestamp":1787757933591,"version":"build-2784847793"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52450016"],"award-info":[{"award-number":["52450016"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52494974"],"award-info":[{"award-number":["52494974"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3704413.3764445","type":"proceedings-article","created":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T17:08:23Z","timestamp":1761239303000},"page":"151-160","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Beyond Static Populations: Efficient Delay-Constrained Scheduling for Dynamic Users via Deep Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8140-2621","authenticated-orcid":false,"given":"Xun","family":"Wang","sequence":"first","affiliation":[{"name":"IIIS, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8776-9562","authenticated-orcid":false,"given":"Zhuoran","family":"Li","sequence":"additional","affiliation":[{"name":"IIIS, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7341-447X","authenticated-orcid":false,"given":"Longbo","family":"Huang","sequence":"additional","affiliation":[{"name":"IIIS, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,23]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2022.3186879"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3106675"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2018.2869583"},{"key":"e_1_3_2_1_4_1","volume-title":"Dzmitry Bahdanau, and Yoshua Bengio.","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho, Bart Van Merri\u00ebnboer, Dzmitry Bahdanau, and Yoshua Bengio. 2014. On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3146400"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1287\/stsy.2021.0081"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2015.2481183"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3141105"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"1596","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 (Proceedings of Machine Learning Research, Vol. 80), Jennifer Dy and Andreas Krause (Eds.). PMLR, 1587\u20131596. https:\/\/proceedings.mlr.press\/v80\/fujimotol8a.html"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00801"},{"key":"e_1_3_2_1_11_1","volume-title":"Efficiency and Responsiveness. In IEEE INFOCOM 2024-IEEE Conference on Computer Communications. IEEE, 1451\u20131460","author":"Giacomoni Luca","year":"2024","unstructured":"Luca Giacomoni and George Parisis. 2024. Reinforcement Learning-based Congestion Control: A Systematic Evaluation of Fairness, Efficiency and Responsiveness. In IEEE INFOCOM 2024-IEEE Conference on Computer Communications. IEEE, 1451\u20131460."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2019.2963877"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3359911"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2015.2460749"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2024.101119"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9091475"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-018-1715-2"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2019.00125"},{"key":"e_1_3_2_1_19_1","volume-title":"Realtime Multiuser Multicarrier Communications","author":"Li Changkun","year":"2024","unstructured":"Changkun Li, Junyi Jiang, Wei Chen, and Khaled B Letaief. 2024. Realtime Multiuser Multicarrier Communications. IEEE Transactions on Wireless Communications (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.2988908"},{"key":"e_1_3_2_1_21_1","volume-title":"Offline Critic-Guided Diffusion Policy for Multi-User Delay-Constrained Scheduling. arXiv preprint arXiv:2501.12942","author":"Li Zhuoran","year":"2025","unstructured":"Zhuoran Li, Ruishuo Chen, Hai Zhong, and Longbo Huang. 2025. Offline Critic-Guided Diffusion Policy for Multi-User Delay-Constrained Scheduling. arXiv preprint arXiv:2501.12942 (2025)."},{"key":"e_1_3_2_1_22_1","volume-title":"Offline Learning-Based Multi-User Delay-Constrained Scheduling. In 2024 IEEE 21st International Conference on Mobile Ad-Hoc and Smart Systems (MASS). IEEE, 92\u201399","author":"Li Zhuoran","year":"2024","unstructured":"Zhuoran Li, Pihe Hu, and Longbo Huang. 2024. Offline Learning-Based Multi-User Delay-Constrained Scheduling. In 2024 IEEE 21st International Conference on Mobile Ad-Hoc and Smart Systems (MASS). IEEE, 92\u201399."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3244239"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2025.3547985"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2021.3085561"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2023.06.026"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Hongzi Mao Ravi Netravali and Mohammad Alizadeh. 2017. Neural adaptive video streaming with pensieve. In ACM SIGCOMM. 197\u2013210.","DOI":"10.1145\/3098822.3098843"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-022-04328-3"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3001736"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"e_1_3_2_1_31_1","volume-title":"Lin (Eds.)","volume":"33","author":"Pan Ling","year":"2020","unstructured":"Ling Pan, Qingpeng Cai, and Longbo Huang. 2020. Softmax Deep Double Deterministic Policy Gradients. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 11767\u201311777. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/884d247c6f65a96a7da4d1105d584ddd-Paper.pdf"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2018.2878348"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC57260.2024.10571146"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.2968424"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2713168.2713195"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014731"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16123"},{"key":"e_1_3_2_1_38_1","first-page":"1","article-title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","volume":"21","author":"Rashid Tabish","year":"2020","unstructured":"Tabish Rashid, Mikayel Samvelyan, Christian Schroeder de Witt, Gregory Farquhar, Jakob Foerster, and Shimon Whiteson. 2020. Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning. Journal of Machine Learning Research 21, 178 (2020), 1\u201351. http:\/\/jmlr.org\/papers\/v21\/20-081.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3409179"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2874671"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/3237383.3238080"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.2980911"},{"key":"e_1_3_2_1_43_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_44_1","volume-title":"Garnett (Eds.)","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3004964"},{"key":"e_1_3_2_1_46_1","volume-title":"Scheduling Real-time Wireless Traffic: A Network-aided Offline Reinforcement Learning Approach","author":"Wan Jialin","year":"2023","unstructured":"Jialin Wan, Sen Lin, Zhaofeng Zhang, Junshan Zhang, and Tao Zhang. 2023. Scheduling Real-time Wireless Traffic: A Network-aided Offline Reinforcement Learning Approach. IEEE Internet of Things Journal (2023)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2023.0025"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jii.2023.100471"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/DTPI61353.2024.10778821"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2025.125327"},{"key":"e_1_3_2_1_51_1","volume-title":"A survey on robotics with foundation models: toward embodied ai. arXiv preprint arXiv:2402.02385","author":"Xu Zhiyuan","year":"2024","unstructured":"Zhiyuan Xu, Kun Wu, Junjie Wen, Jinming Li, Ning Liu, Zhengping Che, and Jian Tang. 2024. A survey on robotics with foundation models: toward embodied ai. arXiv preprint arXiv:2402.02385 (2024)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737649"},{"key":"e_1_3_2_1_53_1","volume-title":"Scheduling Generative-AI DAGs with Model Serving in Data Centers. In IEEE\/ACM International Symposium on Quality of Service.","author":"Zheng Ying","year":"2024","unstructured":"Ying Zheng, Lei Jiao, Yuedong Xu, Bo An, Xin Wang, and Zongpeng Li. 2024. Scheduling Generative-AI DAGs with Model Serving in Data Centers. In IEEE\/ACM International Symposium on Quality of Service."},{"key":"e_1_3_2_1_54_1","volume-title":"Distributionally robust optimal scheduling with heterogeneous uncertainty information: A framework for hydrogen systems","author":"Zhou Anping","year":"2024","unstructured":"Anping Zhou, Mohammad E Khodayar, and Jianhui Wang. 2024. Distributionally robust optimal scheduling with heterogeneous uncertainty information: A framework for hydrogen systems. IEEE Transactions on Sustainable Energy (2024)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472902"}],"event":{"name":"MobiHoc '25: Twenty-sixth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing","location":"Rice University Houston TX USA","acronym":"MobiHoc '25","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the Twenty-sixth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3704413.3764445","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T17:11:27Z","timestamp":1761239487000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3704413.3764445"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,23]]},"references-count":55,"alternative-id":["10.1145\/3704413.3764445","10.1145\/3704413"],"URL":"https:\/\/doi.org\/10.1145\/3704413.3764445","relation":{},"subject":[],"published":{"date-parts":[[2025,10,23]]},"assertion":[{"value":"2025-10-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}