{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T09:49:19Z","timestamp":1771062559626,"version":"3.50.1"},"reference-count":24,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772377"],"award-info":[{"award-number":["61772377"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672257"],"award-info":[{"award-number":["61672257"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91746206"],"award-info":[{"award-number":["91746206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972296"],"award-info":[{"award-number":["61972296"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702380"],"award-info":[{"award-number":["61702380"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2042020kf0217"],"award-info":[{"award-number":["2042020kf0217"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology planning project of Shenzhen","award":["JCYJ20170818112550194"],"award-info":[{"award-number":["JCYJ20170818112550194"]}]},{"name":"Wuhan Advanced Application","award":["2019010701011419"],"award-info":[{"award-number":["2019010701011419"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1109\/tii.2020.3006199","type":"journal-article","created":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T21:35:38Z","timestamp":1593639338000},"page":"4188-4196","source":"Crossref","is-referenced-by-count":24,"title":["Deep Reinforcement Learning for Smart City Communication Networks"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8295-8359","authenticated-orcid":false,"given":"Zhenchang","family":"Xia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9123-5133","authenticated-orcid":false,"given":"Shan","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1371-5801","authenticated-orcid":false,"given":"Jia","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1382-0679","authenticated-orcid":false,"given":"Yanjiao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5576-2083","authenticated-orcid":false,"given":"Junjie","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Libing","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342085"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2904994"},{"key":"ref12","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/693"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref15","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref18","first-page":"731","article-title":"Pantheon: The training ground for Internet congestion-control research","author":"yan","year":"0","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref19","first-page":"417","article-title":"Mahimahi: Accurate record-and-replay for HTTP","author":"netravali","year":"0","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2020.101522"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2016.2605581"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2005.1496608"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/49.464716"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1400097.1400105"},{"key":"ref2","article-title":"Toward Optimal Performance with Network Assisted TCP at Mobile Edge","author":"abbasloo","year":"0","journal-title":"Proc 2nd USENIX Workshop Hot Topics Edge Comput"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2913535"},{"key":"ref9","first-page":"3050","article-title":"A deep reinforcement learning perspective on internet congestion control","author":"jay","year":"0","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3232755.3232783"},{"key":"ref22","first-page":"395","article-title":"PCC: Re-architecting congestion control for consistent high performance","author":"dong","year":"0","journal-title":"Proc USENIX Symp Netw Syst Des Implementation"},{"key":"ref21","first-page":"343","article-title":"PCC Vivace: Online-learning congestion control","author":"dong","year":"0","journal-title":"Proc USENIX Symp Netw Syst Des Implementation"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/248157.248180"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626324"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9424\/9371456\/09130878.pdf?arnumber=9130878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:52:43Z","timestamp":1652194363000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9130878\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":24,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tii.2020.3006199","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6]]}}}