{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T01:08:42Z","timestamp":1780448922205,"version":"3.54.1"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia\/Minist\u00e9rio da Ci\u00eancia Tecnologia e Ensino Superior (FCT\/MCTES) through National Funds and When Applicable Co-Funded EU Funds","doi-asserted-by":"publisher","award":["UIDB\/50008\/2020"],"award-info":[{"award-number":["UIDB\/50008\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3182009","type":"journal-article","created":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T20:37:09Z","timestamp":1654893429000},"page":"62459-62470","source":"Crossref","is-referenced-by-count":7,"title":["Deep Reinforcement Learning Based Routing in IP Media Broadcast Networks: Feasibility and Performance"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8524-0294","authenticated-orcid":false,"given":"Pedro","family":"Amaral","sequence":"first","affiliation":[{"name":"Departamento de Engenharia Electrotécnica e de Computadores, Faculdade de Ciências e Tecnologia (FCT), Universidade Nova de Lisboa, Caparica, Portugal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0896-2602","authenticated-orcid":false,"given":"Diogo","family":"Simoes","sequence":"additional","affiliation":[{"name":"Departamento de Engenharia Electrotécnica e de Computadores, Faculdade de Ciências e Tecnologia (FCT), Universidade Nova de Lisboa, Caparica, Portugal"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5594\/J16131"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5594\/SMPTE.OV2110-0.2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/BMSB53066.2021.9547091"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2021.3105026"},{"key":"ref5","volume-title":"Network Management System Designed for Monitoring, Maintaining and Optimizing your Operation","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICWR.2019.8765278"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2019.2921589"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2946707"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2021.107891"},{"key":"ref10","first-page":"1","article-title":"Learning collaborative policies to solve NP-hard routing problems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Kim"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3314148.3314357"},{"key":"ref12","volume-title":"Network Flows: Theory, Algorithms, and Applications","author":"Waissi","year":"1994"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2749760"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CloudNet.2014.6968971"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2997465.2997487"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MELCON.2016.7495433"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3099092"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref19","article-title":"Playing atari with deep reinforcement learning","volume-title":"arXiv:1312.5602","author":"Mnih","year":"2013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3307363.3307404"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1800097"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2877686"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2020.3017751"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2020.3022064"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ColComCon.2014.6860404"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.3139\/9783446466081","volume-title":"Deep Reinforcement Learning in Action","author":"Zai","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","volume-title":"arXiv:1412.6980","author":"Kingma","year":"2014"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09793657.pdf?arnumber=9793657","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T02:38:50Z","timestamp":1706755130000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9793657\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3182009","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}