{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:07:28Z","timestamp":1767337648912,"version":"3.37.3"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1704662","1704092"],"award-info":[{"award-number":["1704662","1704092"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Select. Areas Commun."],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1109\/jsac.2019.2904358","type":"journal-article","created":{"date-parts":[[2019,3,11]],"date-time":"2019-03-11T18:29:43Z","timestamp":1552328983000},"page":"1325-1336","source":"Crossref","is-referenced-by-count":153,"title":["Experience-Driven Congestion Control: When Multi-Path TCP Meets Deep Reinforcement Learning"],"prefix":"10.1109","volume":"37","author":[{"given":"Zhiyuan","family":"Xu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4418-0114","authenticated-orcid":false,"given":"Jian","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Chengxiang","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Yanzhi","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5833-8894","authenticated-orcid":false,"given":"Guoliang","family":"Xue","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015","journal-title":"Proc ICML"},{"journal-title":"tcpdump","year":"0","key":"ref38"},{"journal-title":"The Mathematics of Internet Congestion Control","year":"2012","author":"srikant","key":"ref33"},{"key":"ref32","first-page":"1","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc ICML"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/9781119453765"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84882-765-3_2"},{"journal-title":"TFLearn","year":"0","key":"ref37"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref36"},{"key":"ref35","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc NIPS"},{"key":"ref34","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc NIPS"},{"key":"ref10","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"hasselt","year":"2016","journal-title":"Proc AAAI"},{"journal-title":"Wireshark","year":"0","key":"ref40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP.2011.6089073"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/248157.248180"},{"journal-title":"Iperf3","year":"0","key":"ref14"},{"key":"ref15","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2011.120211.111818"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2413176.2413178"},{"key":"ref18","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/90.811451"},{"key":"ref28","first-page":"1","article-title":"How hard can it be? Designing and implementing a deployable multipath TCP","author":"raiciu","year":"2012","journal-title":"Proc USENIX NSDI"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2016.2584615"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.17487\/rfc6356"},{"key":"ref3","first-page":"1","article-title":"PCC: Re-architecting congestion control for consistent high performance","author":"dong","year":"2015","journal-title":"Proc USENIX NSDI"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.17487\/rfc6824"},{"journal-title":"Prioritized experience replay","year":"2015","author":"schaul","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2016.7524599"},{"journal-title":"Q-prop Sample-efficient policy gradient with an off-policy critic","year":"2016","author":"gu","key":"ref8"},{"key":"ref7","first-page":"2829","article-title":"Continuous deep Q-Learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/49.464716"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/18.825799"},{"journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems","year":"2016","author":"abadi","key":"ref1"},{"key":"ref46","first-page":"508","article-title":"Goodput improvement for multipath TCP by congestion window adaptation in multi-radio devices","author":"zhou","year":"2013","journal-title":"Proc IEEE CCNC"},{"key":"ref20","first-page":"378","article-title":"Multipath congestion control for shared bottleneck","author":"michio","year":"2009","journal-title":"Proc PFLDnet Workshop"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8057182"},{"key":"ref22","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc ICML"},{"key":"ref21","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":"ref42","first-page":"1","article-title":"Delay-based congestion control for multipath TCP","author":"cao","year":"2012","journal-title":"Proc IEEE ICNP"},{"journal-title":"MultiPath TCP in the Linux Kernel","year":"0","author":"paasch","key":"ref24"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486020"},{"journal-title":"Netem","year":"0","key":"ref23"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787498"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2014.2379698"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2006.879350"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/49\/8715825\/8664598-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/49\/8715825\/08664598.pdf?arnumber=8664598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:09:14Z","timestamp":1657746554000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8664598\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":46,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jsac.2019.2904358","relation":{},"ISSN":["0733-8716","1558-0008"],"issn-type":[{"type":"print","value":"0733-8716"},{"type":"electronic","value":"1558-0008"}],"subject":[],"published":{"date-parts":[[2019,6]]}}}