{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T06:54:17Z","timestamp":1773557657247,"version":"3.50.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF awards","doi-asserted-by":"publisher","award":["1836906"],"award-info":[{"award-number":["1836906"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF awards","doi-asserted-by":"publisher","award":["1908574"],"award-info":[{"award-number":["1908574"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw. Serv. Manage."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/tnsm.2022.3215669","type":"journal-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T21:39:41Z","timestamp":1667511581000},"page":"1644-1659","source":"Crossref","is-referenced-by-count":11,"title":["Partially Oblivious Congestion Control for the Internet via Reinforcement Learning"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2835-5455","authenticated-orcid":false,"given":"Alessio","family":"Sacco","sequence":"first","affiliation":[{"name":"DAUIN, Politecnico di Torino, Turin, Italy"}]},{"given":"Matteo","family":"Flocco","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Saint Louis University, St. Louis, MO, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7798-4584","authenticated-orcid":false,"given":"Flavio","family":"Esposito","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Saint Louis University, St. Louis, MO, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3588-9367","authenticated-orcid":false,"given":"Guido","family":"Marchetto","sequence":"additional","affiliation":[{"name":"DAUIN, Politecnico di Torino, Turin, Italy"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2010.12.012"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2020.2980899"},{"key":"ref56","year":"2022","journal-title":"RYU Controller"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3232755.3232783"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626324"},{"key":"ref14","first-page":"395","article-title":"PCC: Re-architecting congestion control for consistent high performance","author":"dong","year":"2015","journal-title":"Proc 12th USENIX Symp Netw Syst Design Implement (NSDI)"},{"key":"ref58","first-page":"731","article-title":"Pantheon: The training ground for Internet congestion-control research","author":"yan","year":"2018","journal-title":"Proc USENIX Annu Tech Conf (USENIX ATC)"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1002\/spe.981"},{"key":"ref52","first-page":"30","article-title":"Restructuring endpoint congestion control","author":"narayan","year":"2018","journal-title":"Proc Annu Conf ACM Spec Interest Group Data Commun (SIGCOMM)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICBN.2005.1589652"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ColComCon.2014.6860404"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/DCOSS.2016.8"},{"key":"ref54","first-page":"417","article-title":"Mahimahi: Accurate record-and-replay for HTTP","author":"netravali","year":"2015","journal-title":"Proc USENIX Annu Tech Conf (USENIX ATC)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2018.2835758"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3229543.3229550"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/205511.205512"},{"key":"ref18","first-page":"353","article-title":"ABC: A simple explicit congestion controller for wireless networks","author":"goyal","year":"2020","journal-title":"Proc 17th USENIX Symp Netw Syst Des Implement (NSDI)"},{"key":"ref51","article-title":"MVFST-RL: An asynchronous RL framework for congestion control with delayed actions","author":"sivakumar","year":"2019","journal-title":"arXiv 1910 04054"},{"key":"ref50","article-title":"A closer look at invalid action masking in policy gradient algorithms","author":"huang","year":"2020","journal-title":"arXiv 2006 14171"},{"key":"ref46","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2016.05.004"},{"key":"ref48","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn (ICML)"},{"key":"ref47","article-title":"Reinforcement learning for robots using neural networks","author":"lin","year":"1993"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref41","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1851182.1851192"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787498"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2043164.2018443"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2398776.2398810"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486006"},{"key":"ref6","first-page":"459","article-title":"Stochastic forecasts achieve high throughput and low delay over cellular networks","author":"winstein","year":"2013","journal-title":"Proc 10th USENIX Symp Netw Syst Des Implement (NSDI)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3406591"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405892"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405891"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/633025.633035"},{"key":"ref36","first-page":"15","article-title":"Design and implementation of a routing control platform","author":"caesar","year":"2005","journal-title":"Proc USENIX Symp Netw Syst Design Implement (NSDI)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-016-1242-y"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1186\/s13174-018-0087-2"},{"key":"ref33","first-page":"343","article-title":"PCC vivace: Online-learning congestion control","author":"dong","year":"2018","journal-title":"Proc 15th USENIX Symp Netw Syst Des Implement (NSDI)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-009-0228-4"},{"key":"ref2","author":"paxson","year":"2988","journal-title":"Computing TCPs Retransmission Timer"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488851"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342085"},{"key":"ref38","first-page":"1","article-title":"Toward optimal performance with network assisted TCP at mobile edge","author":"abbasloo","year":"2019","journal-title":"Proc 2nd USENIX Workshop Hot Topics Edge Comput (HotEdge)"},{"key":"ref71","first-page":"6158","article-title":"Learning and generalization in overparameterized neural networks, going beyond two layers","author":"allen-zhu y li","year":"2019","journal-title":"Proc Int Conf Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref70","first-page":"1480","article-title":"DARLA: Improving zero-shot transfer in reinforcement learning","author":"higgins","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref73","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","author":"cobbe","year":"2019","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref72","first-page":"6648","article-title":"On the generalization gap in reparameterizable reinforcement learning","author":"wang","year":"2019","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/49.464716"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-3800(02)00064-9"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/248157.248180"},{"key":"ref67","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"simonyan","year":"2013","journal-title":"arXiv 1312 6034"},{"key":"ref26","year":"2022","journal-title":"Geni Exploring Networks of the Future"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3012426.3022184"},{"key":"ref69","article-title":"Transfer learning in deep reinforcement learning: A survey","author":"zhu","year":"2020","journal-title":"arXiv 2009 07888"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/0376-5075(78)90028-4"},{"key":"ref63","year":"2020","journal-title":"Northbound Networks"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1400097.1400105"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1002\/wics.101"},{"key":"ref21","first-page":"3050","article-title":"A deep reinforcement learning perspective on Internet congestion control","author":"jay","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn (ICML)"},{"key":"ref65","author":"jain","year":"1984","journal-title":"A quantitative measure of fairness and discrimination for resource allocation in shared computer systems"},{"key":"ref28","first-page":"2490","article-title":"FAST TCP: Motivation, architecture, algorithms, performance","volume":"4","author":"jin","year":"2004","journal-title":"Proc IEEE INFOCOM Conf Comput Commun"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2006.188"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3281411.3281430"},{"key":"ref60","author":"shalunov","year":"6817","journal-title":"Low Extra Delay Background Transport (LEDBAT)"},{"key":"ref62","volume":"91","author":"bergkvist","year":"2012","journal-title":"WebRTC 1 0 Real-time Communication between Browsers"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/2630088.2631976"}],"container-title":["IEEE Transactions on Network and Service Management"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/4275028\/10168539\/9925110-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4275028\/10168539\/09925110.pdf?arnumber=9925110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T17:45:35Z","timestamp":1689615935000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9925110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":73,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnsm.2022.3215669","relation":{},"ISSN":["1932-4537","2373-7379"],"issn-type":[{"value":"1932-4537","type":"electronic"},{"value":"2373-7379","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}