{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T16:41:24Z","timestamp":1792168884104,"version":"4.4.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong RGC TRS","award":["T41- 603\/20-R"],"award-info":[{"award-number":["T41- 603\/20-R"]}]},{"name":"GRF","award":["16213621"],"award-info":[{"award-number":["16213621"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402407"],"award-info":[{"award-number":["62402407"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"TACC [50]"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/ton.2026.3653773","type":"journal-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T20:57:57Z","timestamp":1768337877000},"page":"2966-2980","source":"Crossref","is-referenced-by-count":2,"title":["Towards Fair and Efficient Congestion Control Through Multi-Agent Deep Reinforcement Learning"],"prefix":"10.1109","volume":"34","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"}]},{"given":"Xudong","family":"Liao","sequence":"additional","affiliation":[{"name":"iSing Laboratory, The Hong Kong University of Science and Technology, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5151-0997","authenticated-orcid":false,"given":"Chaoliang","family":"Zeng","sequence":"additional","affiliation":[{"name":"BitIntelligence, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinchen","family":"Wan","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, 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\/0000-0001-9467-6092","authenticated-orcid":false,"given":"Bing","family":"Xia","sequence":"additional","affiliation":[{"name":"Zhongyuan University of Technology, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2587-6028","authenticated-orcid":false,"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"iSing Laboratory, The Hong Kong University of Science and Technology, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/52325.52356"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1400097.1400105"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3012426.3022184"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/190314.190317"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2006.188"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2004.1354670"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/633025.633035"},{"key":"ref8","first-page":"395","article-title":"PCC: Re-architecting congestion control for consistent high performance","volume-title":"Proc. 12th USENIX Symp. Netw. Syst. Design Implement. (NSDI)","author":"Dong"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626324"},{"key":"ref10","first-page":"343","article-title":"PCC Vivace: Online-learning congestion control","volume-title":"Proc. 15th USENIX Symp. Networked Syst. Design Implement.","author":"Don"},{"key":"ref11","first-page":"3050","article-title":"A deep reinforcement learning perspective on internet congestion control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jay"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405892"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488851"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519593"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3555050.3569125"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544243"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230551"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/35.267444"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72606-7_86"},{"key":"ref22","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"issue":"45","key":"ref23","article-title":"Throughput fairness index: An explanation","volume":"99","author":"Jain","year":"1999","journal-title":"ATM Forum Contribution"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref25","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017","journal-title":"arXiv:1706.02275"},{"key":"ref26","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Iqbal"},{"key":"ref27","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"Rashid","year":"2018","journal-title":"arXiv:1803.11485"},{"key":"ref28","first-page":"178:1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref29","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref30","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref31","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. ICML","author":"Fujimoto"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2631455"},{"key":"ref33","volume-title":"Pantheon Tunnel","year":"2024"},{"key":"ref34","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. ICML","author":"Mnih"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3232755.3232783"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1030194.1015499"},{"key":"ref38","volume-title":"Linux TC"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098840"},{"key":"ref40","first-page":"459","article-title":"Stochastic forecasts achieve high throughput and low delay over cellular networks","volume-title":"Proc. USENIX NSDI","author":"Winstein"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544229"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.17487\/rfc2582"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.2307\/3010473"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1851182.1851192"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787484"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787510"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342085"},{"key":"ref48","first-page":"731","article-title":"Pantheon: The training ground for internet congestion-control research","volume-title":"Proc. USENIX ATC","author":"Yan"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3330737"},{"key":"ref50","article-title":"TACC: A full-stack cloud computing infrastructure for machine learning tasks","author":"Xu","year":"2021","journal-title":"arXiv:2110.01556"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11317935\/11348935.pdf?arnumber=11348935","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:48:33Z","timestamp":1772225313000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11348935\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/ton.2026.3653773","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}