{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T20:11:40Z","timestamp":1783973500722,"version":"3.55.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1109\/icccn49398.2020.9209750","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T16:59:41Z","timestamp":1601485181000},"page":"1-9","source":"Crossref","is-referenced-by-count":11,"title":["Reinforcement Learning Based Congestion Control in a Real Environment"],"prefix":"10.1109","author":[{"given":"Lei","family":"Zhang","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kewei","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junchen","family":"Pan","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Shi","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Cui","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3342280.3342336"},{"key":"ref33","article-title":"tc: Linux advanced routing and traffic control","year":"0"},{"key":"ref32","article-title":"Onnx runtime: cross-platform, high performance scoring engine for ml models","year":"0"},{"key":"ref31","article-title":"Onnx:open neural network exchange","year":"0"},{"key":"ref30","article-title":"Redis","year":"0"},{"key":"ref37","article-title":"Real-world video adaptation with reinforcement learning","author":"mao","year":"2019","journal-title":"ICML"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1145\/3352020.3352031","article-title":"The case for learning-and-system co-design","volume":"53","author":"liang","year":"2019","journal-title":"ACM SIGOPS Operating Systems Review"},{"key":"ref35","first-page":"395","article-title":"Pcc: Rearchitecting congestion control for consistent high performance","author":"dong","year":"2015","journal-title":"Proceedings of the 4th USENIX Conference on Networked Systems Design and Implementation"},{"key":"ref34","article-title":"Modified tcp congestion avoidance algorithm","author":"jacobson","year":"1990","journal-title":"End2end-Interest Mailing List"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486020"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1145\/3009824","article-title":"Bbr: congestion-based congestion control","volume":"60","author":"yeganeh","year":"2017","journal-title":"Communications of the ACM"},{"key":"ref12","first-page":"731","article-title":"Pantheon: The training ground for internet congestion-control research","author":"yan","year":"2018","journal-title":"USENIX Annual Technical Conference (USENIX ATC)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2017.1700200"},{"key":"ref15","first-page":"3050","article-title":"A deep reinforcement learning perspective on internet congestion control","volume":"97","author":"jay","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67235-9_9"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3219617.3219656"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152441"},{"key":"ref28","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3232755.3232783"},{"key":"ref27","article-title":"Copenai gym","author":"brockman","year":"2016","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3143361.3143378"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/52324.52356"},{"key":"ref29","article-title":"Pytorch","year":"0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2019.2948520"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2006.188"},{"key":"ref7","article-title":"Cubic: A new tcp-friendly high-speed tcp variant","author":"xu","year":"2005","journal-title":"Proc Workshop on Protocols for Fast Long Distance Networks"},{"key":"ref2","article-title":"Stms: Improving mptcp throughput under heterogeneous networks","author":"shi","year":"2018","journal-title":"USENIX Annual Technical Conference"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787498"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2018.053681363"},{"key":"ref20","article-title":"Ns2","year":"0"},{"key":"ref22","first-page":"417","article-title":"Mahimahi: Accurate record-and-replay for http","author":"netravali","year":"2015","journal-title":"USENIX Annual Technical Conference (USENIX ATC)"},{"key":"ref21","article-title":"Internet congestion control via deep reinforcement learning","author":"jay","year":"2018","journal-title":"NeurIPS18"},{"key":"ref24","article-title":"Mvfst-rl: An asynchronous rl framework for congestion control with delayed actions","author":"sivakumar","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/844128.844152"},{"key":"ref26","article-title":"Reinforcement learning for bandwidth estimation and congestion control in real-time communications","author":"fang","year":"2019"},{"key":"ref25","article-title":"Park: An open platform for learning-augmented computer systems","author":"mao","year":"2019","journal-title":"NeurIPS 2019"}],"event":{"name":"2020 29th International Conference on Computer Communications and Networks (ICCCN)","location":"Honolulu, HI, USA","start":{"date-parts":[[2020,8,3]]},"end":{"date-parts":[[2020,8,6]]}},"container-title":["2020 29th International Conference on Computer Communications and Networks (ICCCN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9205796\/9209588\/09209750.pdf?arnumber=9209750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T20:02:39Z","timestamp":1783972959000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9209750\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icccn49398.2020.9209750","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]}}}