{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T08:50:00Z","timestamp":1773046200474,"version":"3.50.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172275"],"award-info":[{"award-number":["62172275"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472176"],"award-info":[{"award-number":["62472176"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61832013"],"award-info":[{"award-number":["61832013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472277"],"award-info":[{"award-number":["62472277"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072304"],"award-info":[{"award-number":["62072304"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471383"],"award-info":[{"award-number":["62471383"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Regional Joint Fund of Guangdong","award":["2020B1515130004"],"award-info":[{"award-number":["2020B1515130004"]}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["21511104700"],"award-info":[{"award-number":["21511104700"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai East Talents Program","award":["2023-177"],"award-info":[{"award-number":["2023-177"]}]},{"name":"Huawei Technologies Company, Ltd.","award":["TC20240918032"],"award-info":[{"award-number":["TC20240918032"]}]},{"name":"Huawei Technologies Company, Ltd.","award":["TC20240831022"],"award-info":[{"award-number":["TC20240831022"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Serv. Comput."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tsc.2024.3517328","type":"journal-article","created":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T18:00:48Z","timestamp":1744394448000},"page":"586-602","source":"Crossref","is-referenced-by-count":7,"title":["An Adaptive and Interpretable Congestion Control Service Based on Multi-Objective Reinforcement Learning"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0378-2311","authenticated-orcid":false,"given":"Jiacheng","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7875-3203","authenticated-orcid":false,"given":"Xu","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Technologies Company, Ltd., Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5963-1810","authenticated-orcid":false,"given":"Feilong","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4981-0496","authenticated-orcid":false,"given":"Peng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8957-6625","authenticated-orcid":false,"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computing Science, Simon Fraser University, Burnaby, BC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0207-9643","authenticated-orcid":false,"given":"Jiadi","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6406-4992","authenticated-orcid":false,"given":"Yanmin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3055-5034","authenticated-orcid":false,"given":"Pheng-Ann","family":"Heng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7986-4244","authenticated-orcid":false,"given":"Laurence T.","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"611","article-title":"AUTO: Adaptive congestion control based on multi-objective reinforcement learning for the satellite-ground integrated network","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Li"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2983528"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2023.3239524"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3345391"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2932905"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544252"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3232755.3232783"},{"key":"ref8","first-page":"3050","article-title":"A deep reinforcement learning perspective on internet congestion control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jay"},{"key":"ref9","first-page":"731","article-title":"Pantheon: The training ground for internet congestion-control research","volume-title":"Proc. USENIX Conf. Usenix Annu. Tech. Conf.","author":"Yan"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405892"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1400097.1400105"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2904994"},{"key":"ref13","article-title":"MVFST-RL: An asynchronous RL framework for congestion control with delayed actions","author":"Sivakumar","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3229543.3229550"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2018.2835758"},{"key":"ref16","first-page":"2490","article-title":"Park: An open platform for learning-augmented computer systems","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mao"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904350"},{"key":"ref18","first-page":"395","article-title":"PCC: Re-architecting congestion control for consistent high performance","volume-title":"Proc. 12th USENIX Conf. Netw. Syst. Des. Implementation","author":"Dong"},{"key":"ref19","first-page":"343","article-title":"PCC vivace: Online-learning congestion control","volume-title":"Proc. 12th USENIX Conf. Netw. Syst. Des. Implementation","author":"Dong"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405891"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405859"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10359-2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036958"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933761"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-022-01018-1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519593"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3167713"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3616864"},{"issue":"5","key":"ref31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3527448","article-title":"Explainable deep reinforcement learning: State of the art and challenges","volume":"55","author":"Vouros","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3543846"},{"key":"ref33","first-page":"2499","article-title":"Verifiable reinforcement learning via policy extraction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bastani"},{"key":"ref34","first-page":"10684","article-title":"Symbolic distillation for learned TCP congestion control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sharan"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_28"},{"key":"ref36","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2004.842673"},{"key":"ref38","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schulman"},{"key":"ref39","first-page":"14610","article-title":"A generalized algorithm for multi-objective reinforcement learning and policy adaptation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/0045-7825(89)90053-4"},{"key":"ref41","article-title":"Neural networks are decision trees","author":"Aytekin","year":"2022"},{"key":"ref42","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref43","first-page":"801","article-title":"On the generalization ability of online strongly convex programming algorithms","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kakade"},{"key":"ref44","article-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"ref45","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref46","article-title":"UDT: A high performance data transport protocol","author":"Gu","year":"2005"},{"key":"ref47","article-title":"The coco-beholder: Enabling comprehensive evaluation of congestion control algorithms","author":"Khasina","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405850"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3012426.3022184"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN.2010.5560080"},{"key":"ref51","article-title":"Reinforcement learning for bandwidth estimation and congestion control in real-time communications","author":"Fang","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626324"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/190314.190317"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ISADS.2011.86"}],"container-title":["IEEE Transactions on Services Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4629386\/10964032\/10798476.pdf?arnumber=10798476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T17:37:29Z","timestamp":1744738649000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10798476\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":55,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tsc.2024.3517328","relation":{},"ISSN":["1939-1374","2372-0204"],"issn-type":[{"value":"1939-1374","type":"electronic"},{"value":"2372-0204","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}