{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T02:08:30Z","timestamp":1747274910766,"version":"3.37.3"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001872","name":"Spanish Centre for the Development of Industrial Technology (CDTI) through the Project \u00c9GIDA\u2014RED DE EXCELENCIA EN TECNOLOGIAS DE SEGURIDAD Y PRIVACIDAD","doi-asserted-by":"publisher","award":["CER20191012"],"award-info":[{"award-number":["CER20191012"]}],"id":[{"id":"10.13039\/501100001872","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Spanish Ministry of Science and Innovation","doi-asserted-by":"publisher","award":["PID2019-104966GB-I00"],"award-info":[{"award-number":["PID2019-104966GB-I00"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003086","name":"Basque Business Development Agency (SPRI)-Basque Country Government ELKARTEK Program through the projects TRUSTIND","doi-asserted-by":"publisher","award":["KK-2020\/00054"],"award-info":[{"award-number":["KK-2020\/00054"]}],"id":[{"id":"10.13039\/501100003086","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003086","name":"3KIA","doi-asserted-by":"publisher","award":["KK-2020\/00049"],"award-info":[{"award-number":["KK-2020\/00049"]}],"id":[{"id":"10.13039\/501100003086","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003086","name":"Basque Country Program of Grants for Research Groups","doi-asserted-by":"publisher","award":["IT-1244-19"],"award-info":[{"award-number":["IT-1244-19"]}],"id":[{"id":"10.13039\/501100003086","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3100706","type":"journal-article","created":{"date-parts":[[2021,7,28]],"date-time":"2021-07-28T20:01:51Z","timestamp":1627502511000},"page":"107184-107199","source":"Crossref","is-referenced-by-count":13,"title":["Towards Autonomous Defense of SDN Networks Using MuZero Based Intelligent Agents"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3510-4606","authenticated-orcid":false,"given":"Jon","family":"Gabirondo-Lopez","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1649-7715","authenticated-orcid":false,"given":"Jon","family":"Egana","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4616-322X","authenticated-orcid":false,"given":"Jose","family":"Miguel-Alonso","sequence":"additional","affiliation":[]},{"given":"Raul","family":"Orduna Urrutia","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(01)00129-1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SERVICES.2019.00051"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1002\/dac.4689"},{"key":"ref31","first-page":"1","article-title":"Anomaly detection technique for intrusion detection in SDN environment using continuous data stream machine learning algorithms","author":"ribeiro","year":"2021","journal-title":"Proc IEEE Int Syst Conf (SysCon)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2020.107688"},{"journal-title":"Reinforcement learning connectionist systems","year":"1987","author":"williams","key":"ref37"},{"key":"ref36","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/s20247148"},{"journal-title":"CVE—Common Vulnerabilities and Exposures (CVE)","year":"2020","key":"ref34"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2020.3016246"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2021.108015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.02.056"},{"article-title":"2021 report: Cyberwarfare in the C-suite","year":"2021","author":"morgan","key":"ref1"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"article-title":"An analysis of stochastic game theory for multiagent reinforcement learning","year":"2000","author":"bowling","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_14"},{"journal-title":"THE NATIONAL VULNERABILITY DATABASE (NVD) OVERVIEW","year":"2013","author":"booth","key":"ref50"},{"journal-title":"Common vulnerability scoring system version 3 1 Specification document","year":"2019","key":"ref51"},{"article-title":"Adam: A method for stochastic optimization","year":"0","author":"kingma","key":"ref57"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1002\/dac.4815"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.103"},{"journal-title":"Ryu Project Team","year":"2014","key":"ref54"},{"journal-title":"MuZero General Open Reimplementation of MuZero","year":"2019","author":"duvaud","key":"ref53"},{"journal-title":"Python Reference Manual","year":"2009","author":"van rossum","key":"ref52"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2014.012214.00180"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2016.2553778"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1355734.1355746"},{"journal-title":"OpenFlow Switch Specification","year":"2013","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10922-020-09575-4"},{"key":"ref15","article-title":"SDN controllers: Benchmarking & performance evaluation","author":"zhu","year":"2019","journal-title":"arXiv 1902 04491"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-017-2414-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/GREE.2013.25"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1093\/jigpal\/jzz060"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s12083-017-0630-0"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2013.8"},{"key":"ref5","first-page":"27","article-title":"ATLANTIC: A framework for anomaly traffic detection, classification, and mitigation in SDN","author":"da silva","year":"2016","journal-title":"Proc IEEE\/IFIP Netw Oper Manage Symp (NOMS)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref7","first-page":"1","article-title":"Finding effective security strategies through reinforcement learning and self-play","author":"hammar","year":"2020","journal-title":"Proc 16th Int Conf Netw Service Manage (CNSM)"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/701405"},{"journal-title":"Software-defined networking","year":"2016","author":"duan","key":"ref9"},{"key":"ref46","first-page":"1","article-title":"Ryu: Network operating system","author":"morita","year":"2012","journal-title":"Proc OpenStack Design Summit Conf"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1868447.1868466"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/MSECP.2003.1193207"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.08.021"},{"key":"ref42","first-page":"1407","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","author":"espeholt","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref41","first-page":"1","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","volume":"abs 1712 1815","author":"silver","year":"2017","journal-title":"CoRR"},{"key":"ref44","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018","journal-title":"arXiv 1803 00933"},{"key":"ref43","first-page":"1","article-title":"Recurrent experience replay in distributed reinforcement learning","author":"kapturowski","year":"2018","journal-title":"Proc Int Conf Learn Represent"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09499101.pdf?arnumber=9499101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:57:49Z","timestamp":1639771069000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9499101\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3100706","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}