{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T15:49:45Z","timestamp":1772552985858,"version":"3.50.1"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T00:00:00Z","timestamp":1716163200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T00:00:00Z","timestamp":1716163200000},"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":[[2024,5,20]]},"DOI":"10.1109\/infocom52122.2024.10621288","type":"proceedings-article","created":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T17:25:41Z","timestamp":1723483541000},"page":"1451-1460","source":"Crossref","is-referenced-by-count":12,"title":["Reinforcement Learning-based Congestion Control: A Systematic Evaluation of Fairness, Efficiency and Responsiveness"],"prefix":"10.1109","author":[{"given":"Luca","family":"Giacomoni","sequence":"first","affiliation":[{"name":"University of Sussex,School of Engineering and Informatics"}]},{"given":"George","family":"Parisis","sequence":"additional","affiliation":[{"name":"University of Sussex,School of Engineering and Informatics"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref5","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04301-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2913776"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240545"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2879433"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121870"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3040957"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1800109"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2760281"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1400097.1400105"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3012426.3022184"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2007.896240"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2892046"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933761"},{"key":"ref21","article-title":"A deep reinforcement learning perspective on Internet congestion control","volume-title":"Proc. of ICML","author":"Jay"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405892"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3555050.3569125"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2413176.2413206"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2018.2835758"},{"key":"ref26","article-title":"Learning in situ: a randomized experiment in video streaming","volume-title":"Proc. of USENIX NSDI","author":"Yan"},{"key":"ref27","article-title":"RayNet: A simulation platform for developing reinforcement learning-driven network protocols","volume":"abs\/2302.04519","author":"Giacomoni","year":"2023","journal-title":"CoRR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3345768.3355908"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604838"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45351-2_25"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.07.026"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/IFIPNetworking.2018.8696830"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2006.11.009"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155250"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3185253"},{"key":"ref36","article-title":"Iperf: The TCP\/UDP bandwidth measurement tool","author":"Tirumala","year":"1999"},{"key":"ref37","article-title":"TCP testing (tcpprobe)","volume-title":"The Linux Foundation","author":"Hemminger","year":"2011"},{"key":"ref38","article-title":"SYSSTAT home page","volume-title":"Information and code","author":"Godard","year":"2015"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1868447.1868466"},{"key":"ref40","article-title":"Code for reinforcement learning-based congestion control: A systematic evaluation of fairness, efficiency and responsiveness","author":"Giacomoni","year":"2024"},{"key":"ref41","article-title":"Data for reinforcement learning-based congestion control: A systematic evaluation of fairness, efficiency and responsiveness","author":"Giacomoni","year":"2024"},{"key":"ref42","article-title":"PCC Vivace: Online-learning congestion control","volume-title":"Proc. of USENIX NSDI","author":"Dong"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/DCOSS.2016.8"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904358"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519593"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230553"},{"key":"ref47","first-page":"731","article-title":"Pantheon: the training ground for internet congestion-control research","volume-title":"Proc. of USENIX ATC","author":"Yan"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2631455"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3229543.3229550"},{"key":"ref50","article-title":"Maven: Multi-agent variational exploration","volume":"32","author":"Mahajan","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref51","article-title":"Weighted qmix: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"33","author":"Rashid","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-021-00152-6"}],"event":{"name":"IEEE INFOCOM 2024 - IEEE Conference on Computer Communications","location":"Vancouver, BC, Canada","start":{"date-parts":[[2024,5,20]]},"end":{"date-parts":[[2024,5,23]]}},"container-title":["IEEE INFOCOM 2024 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10621050\/10621073\/10621288.pdf?arnumber=10621288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T05:26:35Z","timestamp":1723526795000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10621288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,20]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/infocom52122.2024.10621288","relation":{},"subject":[],"published":{"date-parts":[[2024,5,20]]}}}