{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:20:13Z","timestamp":1755998413943,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,17]],"date-time":"2023-05-17T00:00:00Z","timestamp":1684281600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,17]],"date-time":"2023-05-17T00:00:00Z","timestamp":1684281600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,17]]},"DOI":"10.1109\/svcc56964.2023.10165310","type":"proceedings-article","created":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T17:20:30Z","timestamp":1688145630000},"page":"1-8","source":"Crossref","is-referenced-by-count":5,"title":["A Curriculum Framework for Autonomous Network Defense using Multi-agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Robert G.","family":"Campbell","sequence":"first","affiliation":[{"name":"San José State University (SJSU),Computer Engineering Department,San José,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Magdalini","family":"Eirinaki","sequence":"additional","affiliation":[{"name":"San José State University (SJSU),Computer Engineering Department,San José,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Younghee","family":"Park","sequence":"additional","affiliation":[{"name":"San José State University (SJSU),Computer Engineering Department,San José,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Creating pro-level AI for real-time fighting game with deep reinforcement learning","volume":"abs 1904 3821","author":"oh","year":"2019","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref15","article-title":"Dota 2 with large scale deep reinforcement learning","volume":"abs 1912 6680","author":"berner","year":"2019","journal-title":"CoRR"},{"key":"ref14","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":"ref11","article-title":"Survey of self-play in reinforcement learning","volume":"abs 2107 2850","author":"digiovanni","year":"2021","journal-title":"CoRR"},{"journal-title":"Deep Reinforcement Learning Hands-On","year":"2018","author":"lapan","key":"ref10"},{"journal-title":"Colonial pipeline cyber incident","year":"2021","key":"ref2"},{"journal-title":"Xforce threat intelligence index 2022","year":"2022","author":"security","key":"ref1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/technologies9030044"},{"key":"ref16","article-title":"Mastering atari, go, chess and shogi by planning with a learned model","volume":"abs 1911 8265","author":"schrittwieser","year":"2019","journal-title":"CoRR"},{"journal-title":"CVSS v3 1 Specification Document","year":"0","key":"ref19"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2006.145"},{"key":"ref24","article-title":"Emergent complexity via multi-agent competition","volume":"abs 1710 3748","author":"bansal","year":"2017","journal-title":"CoRR"},{"key":"ref23","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"ICML"},{"journal-title":"Ray 1 11 1","year":"0","key":"ref26"},{"key":"ref25","article-title":"Ray rllib: A composable and scalable reinforcement learning library","volume":"abs 1712 9381","author":"liang","year":"2017","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"journal-title":"Autonomous network defense using multi-agent reinforcement learning and self-play","year":"2022","author":"campbell","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2013.8"},{"key":"ref28","article-title":"Pettingzoo: Gym for multi-agent reinforcement learning","volume":"abs 2009 14471","author":"terry","year":"2020","journal-title":"CoRR"},{"key":"ref27","article-title":"Openai gym","volume":"abs 1606 1540","author":"brockman","year":"2016","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01554-1_9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3100706"},{"journal-title":"Dynamic Programming and Markov Processes","year":"1960","author":"howard","key":"ref9"},{"journal-title":"Generative adversarial networks","year":"2014","author":"goodfellow","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/CNSM50824.2020.9269092"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121870"}],"event":{"name":"2023 Silicon Valley Cybersecurity Conference (SVCC)","start":{"date-parts":[[2023,5,17]]},"location":"San Jose, CA, USA","end":{"date-parts":[[2023,5,19]]}},"container-title":["2023 Silicon Valley Cybersecurity Conference (SVCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10164830\/10164852\/10165310.pdf?arnumber=10165310","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T17:34:25Z","timestamp":1689615265000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10165310\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,17]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/svcc56964.2023.10165310","relation":{},"subject":[],"published":{"date-parts":[[2023,5,17]]}}}