{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T22:24:52Z","timestamp":1776983092877,"version":"3.51.4"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,10]],"date-time":"2021-05-10T00:00:00Z","timestamp":1620604800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,10]],"date-time":"2021-05-10T00:00:00Z","timestamp":1620604800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,10]],"date-time":"2021-05-10T00:00:00Z","timestamp":1620604800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,10]]},"DOI":"10.1109\/infocom42981.2021.9488863","type":"proceedings-article","created":{"date-parts":[[2021,7,27]],"date-time":"2021-07-27T00:07:32Z","timestamp":1627344452000},"page":"1-10","source":"Crossref","is-referenced-by-count":7,"title":["Leveraging Domain Knowledge for Robust Deep Reinforcement Learning in Networking"],"prefix":"10.1109","author":[{"given":"Ying","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyang","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lixiang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiyang","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuedong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","first-page":"527","article-title":"Network simulations with the ns-3 simulator","volume":"14","author":"henderson","year":"2008","journal-title":"SIGCOMM Demonstration"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152441"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/WiOPT47501.2019.9144110"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3232565.3232569"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408794"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1228"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626296"},{"key":"ref16","first-page":"20","article-title":"Bbr: Congestion-based congestion control","volume":"14","author":"cardwell","year":"2016","journal-title":"Communications of the ACM"},{"key":"ref17","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref18","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in Neural Information Processing Systems(NIPS)"},{"key":"ref19","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref28","article-title":"Interactive learning from policy-dependent human feedback","author":"macglashan","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"ref27","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"ICML"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref29","article-title":"Prioritized experience replay","author":"schaul","year":"2015"},{"key":"ref5","first-page":"3050","article-title":"A deep reinforcement learning perspective on internet congestion control","author":"jay","year":"2019","journal-title":"Int Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155411"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155492"},{"key":"ref2","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240545"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref20","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2015"},{"key":"ref22","article-title":"Variance reduction for reinforcement learning in input-driven environments","author":"mao","year":"2018"},{"key":"ref21","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Int Conference on Machine Learning"},{"key":"ref24","first-page":"143","article-title":"Safe exploration for reinforcement learning","author":"hans","year":"2008","journal-title":"ESANN"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1400097.1400105"},{"key":"ref26","first-page":"763","article-title":"Knowledge revision for reinforcement learning with abstract mdps","author":"efthymiadis","year":"2015","journal-title":"Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems(AAMAS)"},{"key":"ref25","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc?a","year":"2015","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications","location":"Vancouver, BC, Canada","start":{"date-parts":[[2021,5,10]]},"end":{"date-parts":[[2021,5,13]]}},"container-title":["IEEE INFOCOM 2021 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9488422\/9488423\/09488863.pdf?arnumber=9488863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:43:40Z","timestamp":1652197420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9488863\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,10]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/infocom42981.2021.9488863","relation":{},"subject":[],"published":{"date-parts":[[2021,5,10]]}}}