{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:28:56Z","timestamp":1772724536433,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Canada Technology Demonstration Program"},{"DOI":"10.13039\/501100000038","name":"Canada NSERC Discovery Grant","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61902369"],"award-info":[{"award-number":["61902369"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61936011"],"award-info":[{"award-number":["61936011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Key Lab of Networked Multimedia"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Networking"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1109\/tnet.2020.2979966","type":"journal-article","created":{"date-parts":[[2020,3,25]],"date-time":"2020-03-25T21:03:27Z","timestamp":1585170207000},"page":"1255-1268","source":"Crossref","is-referenced-by-count":34,"title":["DeepCast: Towards Personalized QoE for Edge-Assisted Crowdcast With Deep Reinforcement Learning"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2559-045X","authenticated-orcid":false,"given":"Fangxin","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9439-6725","authenticated-orcid":false,"given":"Cong","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0461-6940","authenticated-orcid":false,"given":"Feng","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6592-1984","authenticated-orcid":false,"given":"Jiangchuan","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4352-6507","authenticated-orcid":false,"given":"Yifei","family":"Zhu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3415-9912","authenticated-orcid":false,"given":"Haitian","family":"Pang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4057-5138","authenticated-orcid":false,"given":"Lifeng","family":"Sun","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","first-page":"226","article-title":"Incremental multi-step Q-learning","author":"peng","year":"1994","journal-title":"Machine Learning Proceedings"},{"key":"ref32","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume":"16","author":"abadi","year":"2016","journal-title":"Proc USENIX OSDI"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.6043737"},{"key":"ref30","year":"2020","journal-title":"Amazon EC2 pricing"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24777-7_16"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741667"},{"key":"ref10","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2014.6847928"},{"key":"ref12","year":"2019","journal-title":"Twitch Irc"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2646182"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-05290-8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787486"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2016.7524428"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009894503716"},{"key":"ref19","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":"ref28","article-title":"Training agent for first-person shooter game with actor-critic curriculum learning","author":"wu","year":"2017","journal-title":"Proc ICLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2910642.2910644"},{"key":"ref27","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2017","journal-title":"Proc ICLR"},{"key":"ref3","year":"2017","journal-title":"Twitch 2017 Year in Review"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2845000"},{"key":"ref29","year":"2016","journal-title":"Measureing broadband america 2016 from federal communications commission"},{"key":"ref5","first-page":"1","article-title":"Mobile edge computing—A key technology towards 5G","volume":"11","author":"hu","year":"2015","journal-title":"ETSI White Paper"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123283"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126703"},{"key":"ref2","year":"2020","journal-title":"Facebook Live Statistics"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737456"},{"key":"ref1","year":"2020","journal-title":"Live Streaming Statstics"},{"key":"ref20","first-page":"5","article-title":"Deep reinforcement learning with double q-learning","volume":"2","author":"van hasselt","year":"2016","journal-title":"Proc 13th AAAI"},{"key":"ref22","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc ICLR"},{"key":"ref21","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume":"48","author":"wang","year":"2016","journal-title":"Proc ICML"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240545"},{"key":"ref26","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc NuerIPS"},{"key":"ref25","volume":"20","author":"hagan","year":"1996","journal-title":"Neural Network Design"}],"container-title":["IEEE\/ACM Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/90\/9119211\/09047133.pdf?arnumber=9047133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:42:04Z","timestamp":1651070524000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9047133\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":35,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnet.2020.2979966","relation":{},"ISSN":["1063-6692","1558-2566"],"issn-type":[{"value":"1063-6692","type":"print"},{"value":"1558-2566","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6]]}}}