{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T10:09:09Z","timestamp":1791972549181,"version":"4.3.4"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100004787","name":"Swedish Research Council","doi-asserted-by":"publisher","award":["2024-06436"],"award-info":[{"award-number":["2024-06436"]}],"id":[{"id":"10.13039\/501100004787","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tifs.2026.3709131","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T19:35:32Z","timestamp":1782934532000},"page":"6544-6559","source":"Crossref","is-referenced-by-count":4,"title":["Adaptive Network Security Policies via Belief Aggregation and Rollout"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1773-8354","authenticated-orcid":false,"given":"Kim","family":"Hammar","sequence":"first","affiliation":[{"name":"School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1857-2301","authenticated-orcid":false,"given":"Yuchao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7434-3239","authenticated-orcid":false,"given":"Tansu","family":"Alpcan","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The University of Melbourne, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2844-3917","authenticated-orcid":false,"given":"Emil C.","family":"Lupu","sequence":"additional","affiliation":[{"name":"Department of Computing, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitri P.","family":"Bertsekas","sequence":"additional","affiliation":[{"name":"School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.1987.232894"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2868220"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121870"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.1870873"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2009.5270307"},{"key":"ref6","first-page":"847","article-title":"PentestGPT: Evaluating and harnessing large language models for automated penetration testing","volume-title":"Proc. 33rd USENIX Secur. Symp. (USENIX Secur.)","author":"Deng"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3310072"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/DSN58291.2024.00042"},{"key":"ref9","first-page":"2741","article-title":"SyzVegas: Beating kernel fuzzing odds with reinforcement learning","volume-title":"Proc. 30th USENIX Secur. Symp. (USENIX Secur.)","author":"Wang"},{"key":"ref10","volume-title":"Dynamic Programming and Optimal Control","volume":"2","author":"Bertsekas","year":"2012"},{"key":"ref11","volume-title":"Rollout, Policy Iteration, and Distributed Reinforcement Learning","author":"Bertsekas","year":"2021"},{"key":"ref12","article-title":"On-line policy improvement using Monte-Carlo search","volume-title":"Advances in Neural Information Processing Systems","volume":"9","author":"Tesauro","year":"1996"},{"key":"ref13","first-page":"619","article-title":"Discretized approximations for POMDP with average cost","volume-title":"Proc. 20th Conf. Uncertainty Artif. Intell.","author":"Yu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2016.0832"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2018.7511249"},{"key":"ref16","volume-title":"A Course in Reinforcement Learning","author":"Bertsekas","year":"2025"},{"key":"ref17","article-title":"Biased aggregation, rollout, and enhanced policy improvement for reinforcement learning","author":"Bertsekas","year":"2019","journal-title":"arXiv:1910.02426"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS59830.2024.10575707"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303818"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110473"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3558600"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2023.3285137"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/9.24227"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i20.38750"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511760778"},{"key":"ref26","article-title":"Optimal security response to network intrusions in IT systems","author":"Hammar","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3729213"},{"key":"ref28","article-title":"On autonomous agents in a cyber defence environment","volume-title":"arXiv:2309.07388","author":"Kiely","year":"2023"},{"key":"ref29","article-title":"Automated cyber defence: A review","author":"Vyas","year":"2023","journal-title":"arXiv:2303.04926"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3605764.3623916"},{"key":"ref31","article-title":"Beyond CAGE: Investigating generalization of learned autonomous network defense policies","author":"Wolk","year":"2022","journal-title":"arXiv:2211.15557"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3488932.3527286"},{"key":"ref33","article-title":"Inroads into autonomous network defence using explained reinforcement learning","author":"Foley","year":"2023","journal-title":"arXiv:2306.09318"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS60453.2023.00138"},{"key":"ref35","first-page":"1","article-title":"RICE: Breaking through the training bottlenecks of reinforcement learning with explanation","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Cheng"},{"key":"ref36","article-title":"An empirical game-theoretic analysis of autonomous cyber-defence agents","author":"Palmer","year":"2025","journal-title":"arXiv:2501.19206"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3583133.3590596"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2024.103871"},{"key":"ref39","article-title":"Learning cyber defence tactics from scratch with multi-agent reinforcement learning","author":"Wiebe","year":"2023","journal-title":"arXiv:2310.05939"},{"key":"ref40","article-title":"Hierarchical multi-agent reinforcement learning for cyber network defense","author":"Singh","year":"2024","journal-title":"arXiv:2410.17351"},{"key":"ref41","article-title":"Depending on yourself when you should: Mentoring LLM with RL agents to become the master in cybersecurity games","volume-title":"arXiv:2403.17674","author":"Yan","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICMCIS61231.2024.10540988"},{"key":"ref43","article-title":"Optimal defender strategies for CAGE-2 using causal modeling and tree search","author":"Hammar","year":"2024","journal-title":"arXiv:2407.11070"},{"key":"ref44","article-title":"General autonomous cybersecurity defense: Learning robust policies for dynamic topologies and diverse attackers","author":"Ramamurthy","year":"2025","journal-title":"arXiv:2506.22706"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2025.3568209"},{"key":"ref46","volume-title":"2020 DevOps Trends Survey","author":"Atlassian","year":"2020"},{"key":"ref47","volume-title":"2024 Observability Forecast Report","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3052090"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-02786-9_15"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2022.3176781"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2819967"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3616599"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1017\/9781139061759"},{"key":"ref54","volume-title":"Adaptive Control","author":"\u00c5str\u00f6m","year":"1995"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(65)90154-X"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781316471104"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/78.984773"},{"key":"ref58","article-title":"Feature-based belief aggregation for partially observable Markov decision problems","author":"Li","year":"2025","journal-title":"arXiv:2507.04646"},{"key":"ref59","volume-title":"Reinforcement Learning and Optimal Control","author":"Bertsekas","year":"2019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1768-8_11"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1040.0129"},{"key":"ref62","volume-title":"Software for the paper \u2018Adaptive Network Security Policies via Belief Aggregation and Rollout\u2019","author":"Hammar","year":"2025"},{"key":"ref63","first-page":"54","article-title":"Incremental pruning: A simple, fast, exact method for partially observable Markov decision processes","volume-title":"Proc. 13th Conf. Uncertainty Artif. Intell.","author":"Cassandra"},{"key":"ref64","volume-title":"Lessons from AlphaZero for Optimal, Model Predictive, and Adaptive Control","author":"Bertsekas","year":"2022"},{"key":"ref65","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proc. 5th Berkeley Symp. Math. Statist. Probab.","volume":"1","author":"MacQueen"},{"key":"ref66","volume-title":"CVE Database","year":"2022"},{"key":"ref67","volume-title":"CWE List","year":"2023"},{"key":"ref68","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref69","first-page":"2020","article-title":"Phasic policy gradient","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Cobbe"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref71","first-page":"1","article-title":"Monte-Carlo planning in large POMDPs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Silver"},{"key":"ref72","article-title":"Approximate solution methods for partially observable Markov and semi-Markov decision processes","author":"Yu","year":"2006"},{"issue":"268","key":"ref73","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref74","first-page":"274","article-title":"CleanRL: High-quality single-file implementations of deep reinforcement learning algorithms","volume":"23","author":"Huang","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref75","article-title":"MITRE ATT&CK: Design and philosophy","author":"Strom","year":"2018"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/263109.263155"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/11313711\/11592598.pdf?arnumber=11592598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T04:58:09Z","timestamp":1784609889000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11592598\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/tifs.2026.3709131","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}