{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:34:06Z","timestamp":1775745246515,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/infocom.2018.8485853","type":"proceedings-article","created":{"date-parts":[[2018,10,18]],"date-time":"2018-10-18T18:45:36Z","timestamp":1539888336000},"page":"1871-1879","source":"Crossref","is-referenced-by-count":357,"title":["Experience-driven Networking: A Deep Reinforcement Learning based Approach"],"prefix":"10.1109","author":[{"given":"Zhiyuan","family":"Xu","sequence":"first","affiliation":[]},{"given":"Jian","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Jingsong","family":"Meng","sequence":"additional","affiliation":[]},{"given":"Weiyi","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yanzhi","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Chi Harold","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Dejun","family":"Yang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SAHCN.2016.7733015"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-84882-765-3_2","article-title":"Load-Balancing: building networks that can support all traffic matrices","author":"zhang-","year":"2010","journal-title":"Algorithms for Next Generation Networks"},{"key":"ref33","year":"0","journal-title":"TensorFlow™"},{"key":"ref32","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref31","author":"srikant","year":"2012","journal-title":"The Mathematics of Internet Congestion Control"},{"key":"ref30","author":"schaul","year":"2015","journal-title":"Prioritized experience replay"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2011.2134866"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486020"},{"key":"ref35","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"0","journal-title":"ICML 2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2010.145"},{"key":"ref10","year":"0","journal-title":"Gurobi Optimizer"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/78.492552"},{"key":"ref12","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"hasselt","year":"0","journal-title":"AAAI 2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486019"},{"key":"ref14","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"0","journal-title":"NIPS 2000"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2010.07.001"},{"key":"ref16","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"ICLR 2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/90.811451"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1355734.1355746"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOT.2001.948886"},{"key":"ref28","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0","journal-title":"ICML 2014"},{"key":"ref4","first-page":"1593","article-title":"DEAR: Delay-bounded energy-constrained adaptive routing in wireless sensor networks","author":"bai","year":"0","journal-title":"IEEE Infocom'2012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/icc.2011.5963245"},{"key":"ref3","author":"arnold","year":"2016","journal-title":"Deep reinforcement learning in large discrete action spaces"},{"key":"ref6","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"0","journal-title":"NIPS 2016"},{"key":"ref29","first-page":"484","volume":"529","author":"silver","year":"2016","journal-title":"Mastering the game of Go with deep neural networks and tree search Nature"},{"key":"ref5","first-page":"120","article-title":"Thiel, RLTE:reinforcement learning for traffic-engineering","author":"einhorn","year":"0","journal-title":"IFIP AIMS'2008"},{"key":"ref8","first-page":"2829","article-title":"Continuous deep Q-Learning with model-based acceleration","author":"gu","year":"0","journal-title":"ICML 2016"},{"key":"ref7","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2013.6567024"},{"key":"ref9","author":"gu","year":"2016","journal-title":"Q-prop Sample-efficient policy gradient with an off-policy critic"},{"key":"ref1","year":"0","journal-title":"ARPANET"},{"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":"ref22","year":"0","journal-title":"Ns-3"},{"key":"ref21","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"ICML 2016"},{"key":"ref24","year":"0","journal-title":"Open shortest path first (ospf)"},{"key":"ref23","year":"0","journal-title":"NSFNet"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2006.879350"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2004.842216"}],"event":{"name":"IEEE INFOCOM 2018 - IEEE Conference on Computer Communications","location":"Honolulu, HI","start":{"date-parts":[[2018,4,16]]},"end":{"date-parts":[[2018,4,19]]}},"container-title":["IEEE INFOCOM 2018 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8464035\/8485803\/08485853.pdf?arnumber=8485853","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T04:24:11Z","timestamp":1598243051000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8485853\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/infocom.2018.8485853","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}