{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:20:53Z","timestamp":1771467653373,"version":"3.50.1"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032080660","type":"print"},{"value":"9783032080677","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-08067-7_3","type":"book-chapter","created":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T20:37:20Z","timestamp":1760301440000},"page":"43-60","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Nash Q-Network for\u00a0Multi-agent Cybersecurity Simulation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2287-5049","authenticated-orcid":false,"given":"Qintong","family":"Xie","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2049-6274","authenticated-orcid":false,"given":"Edward","family":"Koh","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8545-0371","authenticated-orcid":false,"given":"Xavier","family":"Cadet","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1913-4223","authenticated-orcid":false,"given":"Peter","family":"Chin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"3_CR1","first-page":"17057","volume":"33","author":"N Brown","year":"2020","unstructured":"Brown, N., Bakhtin, A., Lerer, A., Gong, Q.: Combining deep reinforcement learning and search for imperfect-information games. Adv. Neural. Inf. Process. Syst. 33, 17057\u201317069 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Busoniu, L., Babuska, R., De\u00a0Schutter, B.: A comprehensive survey of multiagent reinforcement learning. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 38(2), 156\u2013172 (2008)","DOI":"10.1109\/TSMCC.2007.913919"},{"issue":"1","key":"3_CR3","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1080\/1350486X.2022.2136727","volume":"29","author":"P Casgrain","year":"2022","unstructured":"Casgrain, P., Ning, B., Jaimungal, S.: Deep Q-learning for NASH equilibria: Nash-DQN. Appl. Math. Fin. 29(1), 62\u201378 (2022)","journal-title":"Appl. Math. Fin."},{"key":"3_CR4","unstructured":"Contractor, F., et\u00a0al.: Learning to communicate in multi-agent reinforcement learning for autonomous cyber Defence (2024)"},{"issue":"2","key":"3_CR5","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1145\/1461928.1461951","volume":"52","author":"C Daskalakis","year":"2009","unstructured":"Daskalakis, C., Goldberg, P.W., Papadimitriou, C.H.: The complexity of computing a Nash equilibrium. Commun. ACM 52(2), 89\u201397 (2009)","journal-title":"Commun. ACM"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Foley, M., Hicks, C., Highnam, K., Mavroudis, V.: Autonomous network Defence using reinforcement learning. In: Proceedings of the 2022 ACM on Asia Conference on Computer and Communications Security, pp. 1252\u20131254 (2022)","DOI":"10.1145\/3488932.3527286"},{"issue":"1","key":"3_CR7","doi-asserted-by":"publisher","first-page":"6","DOI":"10.3390\/info11010006","volume":"11","author":"MC Ghanem","year":"2019","unstructured":"Ghanem, M.C., Chen, T.M.: Reinforcement learning for efficient network penetration testing. Information 11(1), 6 (2019)","journal-title":"Information"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Hammad, A.A., Ahmed, S.R., Abdul-Hussein, M.K., Ahmed, M.R., Majeed, D.A., Algburi, S.: Deep reinforcement learning for adaptive cyber defense in network security. In: Proceedings of the Cognitive Models and Artificial Intelligence Conference, pp. 292\u2013297 (2024)","DOI":"10.1145\/3660853.3660930"},{"key":"3_CR9","first-page":"1039","volume":"4","author":"J Hu","year":"2003","unstructured":"Hu, J., Wellman, M.P.: Nash Q-learning for general-sum stochastic games. J. Mach. Learn. Res. 4, 1039\u20131069 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR10","unstructured":"Kiely, M., Bowman, D., Standen, M., Moir, C.: On autonomous agents in a cyber defence environment. arXiv preprint arXiv:2309.07388 (2023)"},{"key":"3_CR11","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"2","key":"3_CR12","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1137\/0112033","volume":"12","author":"CE Lemke","year":"1964","unstructured":"Lemke, C.E., Howson, J.T.: Equilibrium points of Bimatrix games. J. Soc. Ind. Appl. Math. 12(2), 413\u2013423 (1964)","journal-title":"J. Soc. Ind. Appl. Math."},{"key":"3_CR13","unstructured":"Li, Z., Azizan, N.: Safe multi-agent reinforcement learning with convergence to generalized Nash equilibrium. arXiv preprint arXiv:2411.15036 (2024)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Machine learning proceedings 1994, pp. 157\u2013163. Elsevier (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"3_CR15","doi-asserted-by":"publisher","unstructured":"Louati, F., Ktata, F.B.: A deep learning-based multi-agent system for intrusion detection. SN Appl. Sci. 2(4), 1\u201313 (2020). https:\/\/doi.org\/10.1007\/s42452-020-2414-z","DOI":"10.1007\/s42452-020-2414-z"},{"issue":"2","key":"3_CR16","first-page":"322","volume":"64","author":"D Minehart","year":"1994","unstructured":"Minehart, D., Umanski, J.: Markov perfect equilibrium in a repeated principal-agent relationship. J. Econ. Theory 64(2), 322\u2013340 (1994)","journal-title":"J. Econ. Theory"},{"key":"3_CR17","unstructured":"Moritz, P., et\u00a0al.: Ray: a distributed framework for emerging $$\\{$$AI$$\\}$$ applications. In: 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18), pp. 561\u2013577 (2018)"},{"key":"3_CR18","doi-asserted-by":"publisher","first-page":"157727","DOI":"10.1109\/ACCESS.2021.3129336","volume":"9","author":"M Ozkan-Okay","year":"2021","unstructured":"Ozkan-Okay, M., Samet, R., Aslan, \u00d6., Gupta, D.: A comprehensive systematic literature review on intrusion detection systems. IEEE Access 9, 157727\u2013157760 (2021)","journal-title":"IEEE Access"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Roy, S., Ellis, C., Shiva, S., Dasgupta, D., Shandilya, V., Wu, Q.: A survey of game theory as applied to network security. In: 2010 43rd Hawaii International Conference on System Sciences, pp. 1\u201310. IEEE (2010)","DOI":"10.1109\/HICSS.2010.35"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Silver, D., et\u00a0al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","DOI":"10.1038\/nature16961"},{"key":"3_CR21","unstructured":"Standen, M., Lucas, M., Bowman, D., Richer, T.J., Kim, J., Marriott, D.: CybORG: a gym for the development of autonomous cyber agents. arXiv preprint arXiv:2108.09118 (2021)"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Vinyals, O., et\u00a0al.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","DOI":"10.1038\/s41586-019-1724-z"}],"container-title":["Lecture Notes in Computer Science","Game Theory and AI for Security"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-08067-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T20:37:26Z","timestamp":1760301446000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-08067-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"ISBN":["9783032080660","9783032080677"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-08067-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"13 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"GameSec","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Game Theory and AI for Security","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"gamesec2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.gamesec-conf.org\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}