{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T01:28:09Z","timestamp":1775179689479,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972101"],"award-info":[{"award-number":["61972101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw. Serv. Manage."],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1109\/tnsm.2021.3049298","type":"journal-article","created":{"date-parts":[[2021,1,5]],"date-time":"2021-01-05T21:46:26Z","timestamp":1609883186000},"page":"118-132","source":"Crossref","is-referenced-by-count":52,"title":["DDQP: A Double Deep Q-Learning Approach to Online Fault-Tolerant SFC Placement"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3413-6734","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3328-1764","authenticated-orcid":false,"given":"Weixi","family":"Mao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9807-2648","authenticated-orcid":false,"given":"Jin","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4168-3998","authenticated-orcid":false,"given":"Yuedong","family":"Xu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref38","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959183"},{"key":"ref32","first-page":"36","article-title":"Environment-adaptive sizing and placement of NFV service chains with accelerated reinforcement learning","author":"nakanoya","year":"2019","journal-title":"Proc IFIP\/IEEE Int Symp Integr Netw Manage"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2019.106953"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422444"},{"key":"ref37","first-page":"203","article-title":"NetBricks: Taking the V out of NFV","author":"panda","year":"2016","journal-title":"Proc of the 2nd USENIX Symp on Operating Systems Design and Implementation (OSDI)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959263"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959182"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959181"},{"key":"ref10","first-page":"161","article-title":"Remus: High availability via asynchronous virtual machine replication","author":"cully","year":"2008","journal-title":"Proc USENIX Symp Netw Syst Design Implement (NSDI)"},{"key":"ref40","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":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1899928.1899932"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486320"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3326285.3329056"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref16","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref18","first-page":"2672","article-title":"Tuning recurrent neural networks with reinforcement learning","author":"jaques","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2015.7218511"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7996870"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737400"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2017.2703080"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2015.7045396"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.232"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2785989.2785996"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.17487\/RFC7665"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CloudNet.2015.7335301"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2016.2569020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2018.01.021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639344"},{"key":"ref1","first-page":"163","article-title":"Online fault-tolerant VNF chain placement: A deep reinforcement learning approach","author":"mao","year":"2020","journal-title":"Proc IFIP Netw Conf"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CloudNet.2016.21"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CNSM.2014.7014205"},{"key":"ref45","first-page":"459","article-title":"ClickOS and the art of network function virtualization","author":"martins","year":"2014","journal-title":"Proc USENIX Symp Netw Syst Design Implement (NSDI)"},{"key":"ref48","first-page":"4131","article-title":"Action branching architectures for deep reinforcement learning","author":"tavakoli","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2015.2388585"},{"key":"ref47","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2959058"},{"key":"ref42","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2016.2535401"},{"key":"ref41","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2016.7841846"},{"key":"ref44","year":"2019","journal-title":"Topology zoo dataset"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.2986612"},{"key":"ref43","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2018.2873225"}],"container-title":["IEEE Transactions on Network and Service Management"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4275028\/9374858\/09313044.pdf?arnumber=9313044","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:52:38Z","timestamp":1652194358000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9313044\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3]]},"references-count":48,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnsm.2021.3049298","relation":{},"ISSN":["1932-4537","2373-7379"],"issn-type":[{"value":"1932-4537","type":"electronic"},{"value":"2373-7379","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3]]}}}