{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T19:14:27Z","timestamp":1774120467777,"version":"3.50.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council (NSERC) of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Commun. Netw."],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1109\/tccn.2020.2988908","type":"journal-article","created":{"date-parts":[[2020,4,21]],"date-time":"2020-04-21T19:53:25Z","timestamp":1587498805000},"page":"304-318","source":"Crossref","is-referenced-by-count":70,"title":["Delay-Aware VNF Scheduling: A Reinforcement Learning Approach With Variable Action Set"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7104-7100","authenticated-orcid":false,"given":"Junling","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0627-7567","authenticated-orcid":false,"given":"Weisen","family":"Shi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8781-4925","authenticated-orcid":false,"given":"Ning","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4140-287X","authenticated-orcid":false,"given":"Xuemin","family":"Shen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","author":"sutton","year":"2011","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref38","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":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9014217"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2014.022014.130840"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2629278"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2016.7474348"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS.2014.6838258"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2004.05.002"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.1996.497885"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2927069"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2017.1600248"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2016.2598420"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SaCoNeT.2014.6867768"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICTON.2014.6876564"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1.2.117"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2007.02.014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/NETSOFT.2015.7116120"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2016.2580150"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/CNSM.2017.8256017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/INM.2015.7140281"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2830648"},{"key":"ref27","first-page":"764","article-title":"A neural reinforcement learning approach to learn local dispatching policies in production scheduling","volume":"2","author":"riedmiller","year":"1999","journal-title":"Proc Intern Joint Conf Artificial Intel (IJCAI)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2018.2809473"},{"key":"ref6","year":"2015","journal-title":"The 5G Infrastructure Public Private Partnership the next generation of communication networks and services"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.2986591"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2017.8254072"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2920593"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2864425"},{"key":"ref2","article-title":"5G; Study on scenario and requirements for next generation access technologies, V14.2.0","year":"2018"},{"key":"ref9","article-title":"SDATP: An SDN-based traffic-adaptive and service-oriented transmission protocol","author":"chen","year":"2019","journal-title":"IEEE Trans Cogn Commun Netw"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCChina.2019.8855889"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2010.5641925"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2017.2747509"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1995.488968"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-218X(00)00385-1"},{"key":"ref22","first-page":"2692","article-title":"Pointer networks","author":"vinyals","year":"2015","journal-title":"Proc 28th Int Conf Adv Neural Inf Process Syst"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-0000(75)80008-0"},{"key":"ref21","author":"bello","year":"2016","journal-title":"Neural Combinatorial Optimization with Reinforcement Learning"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2011.571443"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1185"},{"key":"ref23","first-page":"1","article-title":"Adaptive reactive job-shop scheduling with reinforcement learning agents","volume":"24","author":"gabel","year":"2008","journal-title":"Int J Info Technol Intell Comput"},{"key":"ref44","author":"pinedo","year":"2005","journal-title":"Planning and Scheduling in Manufacturing and Services"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2881135"},{"key":"ref43","first-page":"1","article-title":"Convergence of Q-learning: A simple proof","author":"melo","year":"2001"},{"key":"ref25","first-page":"535","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"2000","journal-title":"Proc 17th Int Conf Mach Learn (ICML’00)"}],"container-title":["IEEE Transactions on Cognitive Communications and Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6687307\/9371452\/09075271.pdf?arnumber=9075271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:06Z","timestamp":1652194446000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9075271\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3]]},"references-count":48,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tccn.2020.2988908","relation":{},"ISSN":["2332-7731","2372-2045"],"issn-type":[{"value":"2332-7731","type":"electronic"},{"value":"2372-2045","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3]]}}}