{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T21:07:01Z","timestamp":1761599221640,"version":"3.37.3"},"reference-count":19,"publisher":"IEEE","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\/100016311","name":"Arm","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016311","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016311","name":"Arm","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1109\/icc42927.2021.9500763","type":"proceedings-article","created":{"date-parts":[[2021,8,6]],"date-time":"2021-08-06T20:49:21Z","timestamp":1628282961000},"page":"1-6","source":"Crossref","is-referenced-by-count":7,"title":["A Security-Constrained Reinforcement Learning Framework for Software Defined Networks"],"prefix":"10.1109","author":[{"given":"Anand","family":"Mudgerikar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elisa","family":"Bertino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jorge","family":"Lobo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinesh","family":"Verma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/CISDA.2009.5356528"},{"year":"2016","author":"brockman","article-title":"Openai gym","key":"ref11"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1145\/2656877.2656890"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1145\/1868447.1868466"},{"key":"ref14","first-page":"951","article-title":"Getting traffic statistics from network devices in an sdn environment using openflow","author":"hamad","year":"2015","journal-title":"Information and Systems Technology"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1016\/j.jnca.2016.12.019"},{"year":"2019","author":"reddy","article-title":"Learning human objectives by evaluating hypothetical behavior","key":"ref16"},{"key":"ref17","article-title":"Active learning literature survey","author":"settles","year":"2009","journal-title":"Tech Rep"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/COMST.2017.2745505"},{"key":"ref19","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc?a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","article-title":"Jarvis: Moving towards a smarter internet of things","author":"mudgerikar","year":"2020","journal-title":"40th IEEE International Conference on Distributed Computing Systems"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1016\/j.comnet.2020.107230"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/MSP.2014.31"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1145\/3005714"},{"year":"2018","author":"sutton","journal-title":"Reinforcement Learning An Introduction","key":"ref8"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.5220\/0006639801080116"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/MNET.2018.1800097"},{"year":"2017","author":"stampa","article-title":"A deep-reinforcement learning approach for software-defined networking routing optimization","key":"ref1"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1145\/1355734.1355746"}],"event":{"name":"ICC 2021 - IEEE International Conference on Communications","start":{"date-parts":[[2021,6,14]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2021,6,23]]}},"container-title":["ICC 2021 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9500243\/9500244\/09500763.pdf?arnumber=9500763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:44:12Z","timestamp":1652197452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9500763\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icc42927.2021.9500763","relation":{},"subject":[],"published":{"date-parts":[[2021,6]]}}}