{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T07:49:09Z","timestamp":1791445749608,"version":"4.3.3"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"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":[[2026,9]]},"DOI":"10.1109\/coins69995.2026.11715652","type":"proceedings-article","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T19:21:36Z","timestamp":1791400896000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents"],"prefix":"10.1109","author":[{"given":"Ankita","family":"Samaddar","sequence":"first","affiliation":[{"name":"Vanderbilt University","place":["Nashville, TN"],"department":["Departmaent of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sandeep","family":"Neema","sequence":"additional","affiliation":[{"name":"Vanderbilt University","place":["Nashville, TN"],"department":["Departmaent of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Balasubramanian","sequence":"additional","affiliation":[{"name":"Vanderbilt University","place":["Nashville, TN"],"department":["Departmaent of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xenofon","family":"Koutsoukos","sequence":"additional","affiliation":[{"name":"Vanderbilt University","place":["Nashville, TN"],"department":["Departmaent of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2674"},{"key":"ref2","article-title":"Imitating Latent Policies from Observation","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Edwards"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3834"},{"key":"ref4","article-title":"Learning to Act without Actions","volume-title":"The Twelfth International Conference on Learning Representations (ICLR)","author":"Schmidt"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5220\/0010316901130124"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1201\/9780429489105"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICAA64256.2024.00011"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIC63015.2025.10849024"},{"key":"ref9","article-title":"CybORG: A Gym for the Development of Autonomous Cyber Agents","volume-title":"IJCAI-21 1st International Workshop on Adaptive Cyber Defense","author":"Standen"},{"key":"ref10","article-title":"Beyond CAGE: Investigating Generalization of Learned Autonomous Network Defense Policies","author":"Wolk","year":"2022","journal-title":"NeurIPS"},{"key":"ref11","article-title":"MITRE ATT&CK"},{"key":"ref12","article-title":"On Autonomous Agents in a Cyber Defence Environment","author":"Kiely","year":"2023","journal-title":"ArXiv"},{"key":"ref13","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"2014"},{"key":"ref14","article-title":"Learn-Red-Policy"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3488932.3527286"},{"key":"ref16","article-title":"Network Environment Design for Autonomous Cyberdefense","author":"Molina-Markham","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3605764.3623916"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM58377.2023.10356283"},{"key":"ref19","article-title":"Learning Object-centric Latent Dynamics for Reinforcement Learning from Pixels","volume-title":"The Thirteenth International Conference on Learning Representations (ICLR)","author":"Mosbach"}],"event":{"name":"2026 IEEE International Conference on Omni Layer Intelligent Systems (COINS)","location":"Bologna, Italy","start":{"date-parts":[[2026,9,7]]},"end":{"date-parts":[[2026,9,9]]}},"container-title":["2026 IEEE International Conference on Omni Layer Intelligent Systems (COINS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11715558\/11715560\/11715652.pdf?arnumber=11715652","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T06:49:12Z","timestamp":1791442152000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11715652\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/coins69995.2026.11715652","relation":{},"subject":[],"published":{"date-parts":[[2026,9]]}}}