{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:54:24Z","timestamp":1774022064755,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T00:00:00Z","timestamp":1713139200000},"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":[[2024,4,15]]},"DOI":"10.1145\/3625468.3652183","type":"proceedings-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T06:10:01Z","timestamp":1713334201000},"page":"381-387","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Accurate Bandwidth Prediction for Real-Time Media Streaming with Offline Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9609-033X","authenticated-orcid":false,"given":"Qingyue","family":"Tan","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences and University of Chinese Academy of Sciences"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6158-1345","authenticated-orcid":false,"given":"Gerui","family":"Lv","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences and University of Chinese Academy of Sciences"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5976-2085","authenticated-orcid":false,"given":"Xing","family":"Fang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences and University of Chinese Academy of Sciences"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3637-2273","authenticated-orcid":false,"given":"Jiaxing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences and University of Chinese Academy of Sciences"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7410-9514","authenticated-orcid":false,"given":"Zejun","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences and University of Chinese Academy of Sciences"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1346-3581","authenticated-orcid":false,"given":"Yuan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences and University of Chinese Academy of Sciences"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5526-4984","authenticated-orcid":false,"given":"Qinghua","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences and University of Chinese Academy of Sciences"}]}],"member":"320","published-online":{"date-parts":[[2024,4,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Alomar Abdullah","year":"2023","unstructured":"Abdullah Alomar, Pouya Hamadanian, Arash Nasr-Esfahany, Anish Agarwal, Mohammad Alizadeh, and Devavrat Shah. 2023. {CausalSim}: A Causal Framework for Unbiased {Trace-Driven} Simulation. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 1115--1147."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604828"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2017.2703615"},{"key":"e_1_3_2_1_4_1","volume-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555","author":"Chung Junyoung","year":"2014","unstructured":"Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604822"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922100"},{"key":"e_1_3_2_1_7_1","unstructured":"Scott Fujimoto and Shixiang Gu. 2021. A Minimalist Approach to Offline Reinforcement Learning. In Advances in Neural Information Processing Systems A. Beygelzimer Y. Dauphin P. Liang and J. Wortman Vaughan (Eds.). https:\/\/openreview.net\/forum?id=Q32U7dzWXpc"},{"key":"e_1_3_2_1_8_1","volume-title":"Addressing Function Approximation Error in Actor-Critic Methods. In International Conference on Machine Learning. 1582--1591","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. 1582--1591."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2413176.2413189"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Sami Khairy Gabriel Mittag Scott Inglis Vishak Gopal Mehrsa Golestaneh Ross Cutler Francis Yan and Zhixiong Niu. 2024. ACM MMSys 2024 Bandwidth Estimation in Real Time Communications Challenge. arXiv:2403.06324 [cs.NI]","DOI":"10.1145\/3625468.3653068"},{"key":"e_1_3_2_1_12_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_13_1","unstructured":"Aviral Kumar Aurick Zhou George Tucker and Sergey Levine. 2020. Conservative Q-Learning for Offline Reinforcement Learning. arXiv:2006.04779 [cs.LG]"},{"key":"e_1_3_2_1_14_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_15_1","volume-title":"Chorus: Coordinating Mobile Multipath Scheduling and Adaptive Video Streaming. In The 30th Annual International Conference on Mobile Computing and Networking. 1--17","author":"Lv Gerui","year":"2024","unstructured":"Gerui Lv, Qinghua Wu, Yanmei Liu, Zhenyu Li, Qingyue Tan, Furong Yang, Wentao Chen, Yunfei Ma, Hongyu Guo, Ying Chen, and Gaogang Xie. 2024. Chorus: Coordinating Mobile Multipath Scheduling and Adaptive Video Streaming. In The 30th Annual International Conference on Mobile Computing and Networking. 1--17."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796948"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"e_1_3_2_1_18_1","volume-title":"Hairpin: Rethinking Packet Loss Recovery in Edge-based Interactive Video Streaming. In USENIX NSDI.","author":"Meng Zili","year":"2024","unstructured":"Zili Meng, Xiao Kong, Jing Chen, Bo Wang, Mingwei Xu, Rui Han, Honghao Liu, Venkat Arun, Hongxin Hu, and Xue Wei. 2024. Hairpin: Rethinking Packet Loss Recovery in Edge-based Interactive Video Streaming. In USENIX NSDI."},{"key":"e_1_3_2_1_19_1","unstructured":"Microsoft. 2024. https:\/\/www.microsoft.com\/en-us\/research\/academic-program\/bandwidth-estimation-challenge\/."},{"key":"e_1_3_2_1_20_1","unstructured":"Microsoft. 2024. https:\/\/github.com\/microsoft\/RL4BandwidthEstimationChallenge\/tree\/main\/onnx_models."},{"key":"e_1_3_2_1_21_1","unstructured":"WebRTC project. 2024. https:\/\/webrtc.org\/. Accessed: 2024-02-03."},{"key":"e_1_3_2_1_22_1","volume-title":"Marcos ROA Maximo, and Esther Luna Colombini","author":"Prudencio Rafael Figueiredo","year":"2023","unstructured":"Rafael Figueiredo Prudencio, Marcos ROA Maximo, and Esther Luna Colombini. 2023. A survey on offline reinforcement learning: Taxonomy, review, and open problems. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Rudow Michael","year":"2023","unstructured":"Michael Rudow, Francis Y Yan, Abhishek Kumar, Ganesh Ananthanarayanan, Martin Ellis, and KV Rashmi. 2023. Tambur: Efficient loss recovery for videoconferencing via streaming codes. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 953--971."},{"key":"e_1_3_2_1_24_1","volume-title":"On-line Q-learning using connectionist systems","author":"Rummery Gavin A","unstructured":"Gavin A Rummery and Mahesan Niranjan. 1994. On-line Q-learning using connectionist systems. Vol. 37. University of Cambridge, Department of Engineering Cambridge, UK."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934898"},{"key":"e_1_3_2_1_26_1","volume-title":"CORL: Research-oriented deep offline reinforcement learning library. Advances in Neural Information Processing Systems 36","author":"Tarasov Denis","year":"2023","unstructured":"Denis Tarasov, Alexander Nikulin, Dmitry Akimov, Vladislav Kurenkov, and Sergey Kolesnikov. 2023. CORL: Research-oriented deep offline reinforcement learning library. Advances in Neural Information Processing Systems 36 (2023)."},{"key":"e_1_3_2_1_27_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_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613443"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604819"},{"key":"e_1_3_2_1_30_1","volume-title":"17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Yan Francis Y","year":"2020","unstructured":"Francis Y Yan, Hudson Ayers, Chenzhi Zhu, Sadjad Fouladi, James Hong, Keyi Zhang, Philip Levis, and Keith Winstein. 2020. Learning in situ: a randomized experiment in video streaming. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20). 495--511."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604838"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787486"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483259"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419186"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3345430"}],"event":{"name":"MMSys '24: ACM Multimedia Systems Conference 2024","location":"Bari Italy","acronym":"MMSys '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGCOMM ACM Special Interest Group on Data Communication","SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the ACM Multimedia Systems Conference 2024 on ZZZ"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3625468.3652183","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3625468.3652183","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:29:31Z","timestamp":1755883771000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3625468.3652183"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,15]]},"references-count":35,"alternative-id":["10.1145\/3625468.3652183","10.1145\/3625468"],"URL":"https:\/\/doi.org\/10.1145\/3625468.3652183","relation":{},"subject":[],"published":{"date-parts":[[2024,4,15]]},"assertion":[{"value":"2024-04-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}