{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:21:15Z","timestamp":1772644875806,"version":"3.50.1"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"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":["61871045"],"award-info":[{"award-number":["61871045"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"111 Project of China","award":["B16006"],"award-info":[{"award-number":["B16006"]}]},{"name":"BUPT Excellent Ph.D. Students Foundation","award":["XTCX201806"],"award-info":[{"award-number":["XTCX201806"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2021,2,1]]},"DOI":"10.1109\/jiot.2020.3015042","type":"journal-article","created":{"date-parts":[[2020,8,7]],"date-time":"2020-08-07T21:45:53Z","timestamp":1596836753000},"page":"1830-1845","source":"Crossref","is-referenced-by-count":15,"title":["Game-Theoretic Actor\u2013Critic-Based Intrusion Response Scheme (GTAC-IRS) for Wireless SDN-Based IoT Networks"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9259-9126","authenticated-orcid":false,"given":"Bizhu","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0839-1769","authenticated-orcid":false,"given":"Yan","family":"Sun","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1137-7546","authenticated-orcid":false,"given":"Mengying","family":"Sun","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4245-5989","authenticated-orcid":false,"given":"Xiaodong","family":"Xu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2016.7849837"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/Trustcom.2015.389"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2014.02.001"},{"key":"ref30","first-page":"262","article-title":"Off-policy q-learning technique for intrusion response in network security","volume":"136","author":"stefanova","year":"2018","journal-title":"World Acad Sci Eng Technol Int Sci Index"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1117\/12.2518976"},{"key":"ref36","first-page":"3422","article-title":"Actor–critic policy optimization in partially observable multiagent environments","author":"srinivasan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LCN.2010.5735752"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.bjp.2013.10.014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2019.106871"},{"key":"ref11","author":"ting","year":"2019","journal-title":"Guidelines for 5G End to End Architecture and Security Issues"},{"key":"ref12","year":"2020","journal-title":"A Website by SkyVision Solutions"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2878570"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11235-011-9484-6"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP.2015.58"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2009.10.003"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/09540091.2015.1031082"},{"key":"ref18","author":"nguyen","year":"2019","journal-title":"Deep reinforcement learning for cyber security"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2019.106460"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3220127.3220128"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/iThings\/GreenCom\/CPSCom\/SmartData.2019.00150"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jestch.2015.11.001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCOMSTD.2017.1700031"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10922-020-09532-1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2452921"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.06.026"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2655690"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2017.09.070"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1800394"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WTS.2018.8363932"},{"key":"ref1","year":"2017","journal-title":"ITU-R M [IMT-2020 TECH PERF REQ] Minimum Requirements Related to Technical Performance for IMT–2020 Radio Interface(s)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943056"},{"key":"ref22","first-page":"2817","article-title":"Cold-start reinforcement learning with softmax policy gradient","author":"ding","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref24","author":"degris","year":"2012","journal-title":"Off-Policy Actor–Critic"},{"key":"ref23","first-page":"1008","article-title":"Actor–critic algorithms","author":"konda","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","author":"yang","year":"2017","journal-title":"Notes on TD ($\\lambda $ ) With Eligibility Trace"},{"key":"ref25","first-page":"2775","article-title":"Bridging the gap between value and policy-based reinforcement learning","author":"nachum","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/9334468\/09162048.pdf?arnumber=9162048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:55Z","timestamp":1652194435000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9162048\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,1]]},"references-count":37,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2020.3015042","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,1]]}}}