{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T13:04:54Z","timestamp":1780664694808,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T00:00:00Z","timestamp":1777161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"NSFC","award":["62402407"],"award-info":[{"award-number":["62402407"]}]},{"name":"Hong Kong RGC TRS","award":["T41-603\/20R"],"award-info":[{"award-number":["T41-603\/20R"]}]},{"name":"Hong Kong GRF","award":["16213621"],"award-info":[{"award-number":["16213621"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3767295.3769317","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:20:04Z","timestamp":1777062004000},"page":"108-125","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Learn-to-Probe: Achieving Signal Distinguishability in Learning-based Congestion Control"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3238-8500","authenticated-orcid":false,"given":"Han","family":"Tian","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1068-346X","authenticated-orcid":false,"given":"Wenbo","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6926-7801","authenticated-orcid":false,"given":"Junxue","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8380-1879","authenticated-orcid":false,"given":"Xudong","family":"Liao","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3442-4656","authenticated-orcid":false,"given":"Decang","family":"Sun","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7515-3760","authenticated-orcid":false,"given":"Donghui","family":"Chen","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5526-0201","authenticated-orcid":false,"given":"Bin","family":"Huang","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd., Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8228-2552","authenticated-orcid":false,"given":"Wenxue","family":"Li","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8699-8355","authenticated-orcid":false,"given":"Yong","family":"Wang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2587-6028","authenticated-orcid":false,"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,26]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405892"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/3691825.3691878"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472912"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3232755.3232783"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Lawrence S Brakmo Sean W O'Malley and Larry L Peterson. 1994. TCP Vegas: New techniques for congestion detection and avoidance. Number 4. ACM.","DOI":"10.1145\/190809.190317"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3012426.3022184"},{"key":"e_1_3_2_1_7_1","volume-title":"PCC: Re-architecting Congestion Control for Consistent High Performance. In 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI 15)","author":"Dong Mo","year":"2015","unstructured":"Mo Dong, Qingxi Li, Doron Zarchy, P Brighten Godfrey, and Michael Schapira. 2015. PCC: Re-architecting Congestion Control for Consistent High Performance. In 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI 15). 395\u2013408."},{"key":"e_1_3_2_1_8_1","volume-title":"PCC Vivace: Online-Learning Congestion Control. In 15th USENEC Symposium on Networked Systems Design and Implementation (NSDI 18)","author":"Dong Mo","year":"2018","unstructured":"Mo Dong, Tong Meng, Doron Zarchy, Engin Arslan, Yossi Gilad, Brighten Godfrey, and Michael Schapira. 2018. PCC Vivace: Online-Learning Congestion Control. In 15th USENEC Symposium on Networked Systems Design and Implementation (NSDI 18). USENIX Association, Renton, WA, 343\u2013356."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21020438"},{"key":"e_1_3_2_1_10_1","unstructured":"DI engine Contributors. 2021. DI-engine: OpenDILab Decision Intelligence Engine. https:\/\/github.com\/opendilab\/DI-engine. (2021)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2002.807336"},{"key":"e_1_3_2_1_12_1","volume-title":"International Conference on Machine Learning. PMLR, 1587\u20131596","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\u20131596."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1400097.1400105"},{"key":"e_1_3_2_1_14_1","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Hao Mingzhe","year":"2020","unstructured":"Mingzhe Hao, Levent Toksoz, Nanqinqin Li, Edward Edberg Halim, Henry Hoffmann, and Haryadi S Gunawi. 2020. {LinnOS}: Predictability on Unpredictable Flash Storage with a Light Neural Network. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). 173\u2013190."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP.2017.8117540"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3495759"},{"key":"e_1_3_2_1_17_1","volume-title":"Congestion avoidance and control. ACM SIGCOMM computer communication review 18, 4","author":"Jacobson Van","year":"1988","unstructured":"Van Jacobson. 1988. Congestion avoidance and control. ACM SIGCOMM computer communication review 18, 4 (1988), 314\u2013329."},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Machine Learning ICML. 3050\u20133059","author":"Jay Nathan","year":"2019","unstructured":"Nathan Jay, Noga Rotman, Brighten Godfrey, Michael Schapira, and Aviv Tamar. 2019. A Deep Reinforcement Learning Perspective on Internet Congestion Control. In International Conference on Machine Learning ICML. 3050\u20133059."},{"key":"e_1_3_2_1_19_1","volume-title":"International conference on learning representations.","author":"Kapturowski Steven","year":"2018","unstructured":"Steven Kapturowski, Georg Ostrovski, John Quan, Remi Munos, and Will Dabney. 2018. Recurrent experience replay in distributed reinforcement learning. In International conference on learning representations."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2005.1498463"},{"key":"e_1_3_2_1_21_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3650069"},{"key":"e_1_3_2_1_23_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_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519593"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"e_1_3_2_1_27_1","volume-title":"International conference on machine learning. PMLR","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous methods for deep reinforcement learning. In International conference on machine learning. PMLR, 1928\u20131937."},{"key":"e_1_3_2_1_28_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_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2631455"},{"key":"e_1_3_2_1_30_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.). Curran Associates, Inc., 8024\u20138035. http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"J Salim H Khosravi Andi Kleen and Alexey Kuznetsov. 2003. Linux netlink as an ip services protocol. Technical Report.","DOI":"10.17487\/rfc3549"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"David Silver Thomas Hubert Julian Schrittwieser Ioannis Antonoglou Matthew Lai Arthur Guez Marc Lanctot Laurent Sifre Dharshan Kumaran Thore Graepel et al. 2018. A general reinforcement learning algorithm that masters chess shogi and Go through self-play. Science 362 6419 (2018) 1140\u20131144.","DOI":"10.1126\/science.aar6404"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 31st International Conference on Machine Learning (Proceedings of Machine Learning Research), Eric P. Xing and Tony Jebara (Eds.)","volume":"32","author":"Silver David","year":"2014","unstructured":"David Silver, Guy Lever, Nicolas Heess, Thomas Degris, Daan Wierstra, and Martin Riedmiller. 2014. Deterministic Policy Gradient Algorithms. In Proceedings of the 31st International Conference on Machine Learning (Proceedings of Machine Learning Research), Eric P. Xing and Tony Jebara (Eds.), Vol. 32. PMLR, Bejing, China, 387\u2013395. https:\/\/proceedings.mlr.press\/v32\/silver14.html"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3312046"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2006.188"},{"key":"e_1_3_2_1_36_1","unstructured":"The Google BBR Team. [n. d.]. BBR bandwidth based convergence. ([n. d.]). https:\/\/github.com\/google\/bbr\/blob\/master\/Documentation\/bbr_bandwidth_based_convergence.pdf."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696065"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555050.3569125"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486020"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707266"},{"key":"e_1_3_2_1_41_1","volume-title":"2018 USENIX Annual Technical Conference (USENIX ATC 18)","author":"Yan Francis Y","year":"2018","unstructured":"Francis Y Yan, Jestin Ma, Greg D Hill, Deepti Raghavan, Riad S Wahby, Philip Levis, and Keith Winstein. 2018. Pantheon: the training ground for Internet congestion-control research. In 2018 USENIX Annual Technical Conference (USENIX ATC 18)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472927"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604838"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544229"}],"event":{"name":"EUROSYS '26: 21st European Conference on Computer Systems","location":"McEwan Hall\/The University of Edinburgh Edinburgh Scotland UK","acronym":"EUROSYS '26","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 21st European Conference on Computer Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3767295.3769317","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T12:15:42Z","timestamp":1780661742000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767295.3769317"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,26]]},"references-count":44,"alternative-id":["10.1145\/3767295.3769317","10.1145\/3767295"],"URL":"https:\/\/doi.org\/10.1145\/3767295.3769317","relation":{},"subject":[],"published":{"date-parts":[[2026,4,26]]},"assertion":[{"value":"2026-04-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}