{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T09:25:41Z","timestamp":1743067541759,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031545276"},{"type":"electronic","value":"9783031545283"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-54528-3_4","type":"book-chapter","created":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T07:06:29Z","timestamp":1708585589000},"page":"57-78","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Defeating the\u00a0Non-stationary Opponent Using Deep Reinforcement Learning and\u00a0Opponent Modeling"],"prefix":"10.1007","author":[{"given":"Qian","family":"Yao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinli","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongjie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,23]]},"reference":[{"key":"4_CR1","unstructured":"Baillie, C., Standen, M., Schwartz, J., Docking, M., Bowman, D., Kim, J.: Cyborg: an autonomous cyber operations research gym. arXiv preprint arXiv:2002.10667 (2020)"},{"key":"4_CR2","unstructured":"Everett, R., Roberts, S.J.: Learning against non-stationary agents with opponent modelling and deep reinforcement learning. In: AAAI Spring Symposia (2018)"},{"key":"4_CR3","unstructured":"Foerster, J.N., Chen, R.Y., Al-Shedivat, M., Whiteson, S., Abbeel, P., Mordatch, I.: Learning with opponent-learning awareness. arXiv preprint arXiv:1709.04326 (2017)"},{"key":"4_CR4","unstructured":"Fortunato, M., et al.: Noisy networks for exploration. arXiv preprint arXiv:1706.10295 (2017)"},{"key":"4_CR5","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1007\/978-3-030-93409-5_68","volume-title":"COMPLEX NETWORKS 2021","author":"L Greige","year":"2022","unstructured":"Greige, L., Chin, P.: Deep reinforcement learning for flipit security game. In: Benito, R.M., et al. (eds.) COMPLEX NETWORKS 2021, pp. 831\u2013843. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-93409-5_68"},{"key":"4_CR6","unstructured":"He, H., Boyd-Graber, J., Kwok, K., Daum\u00e9 III, H.: Opponent modeling in deep reinforcement learning. In: International Conference on Machine Learning, pp. 1804\u20131813. PMLR (2016)"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Hernandez-Leal, P., Zhan, Y., Taylor, M.E., Sucar, L.E., Munoz de Cote, E.: An exploration strategy for non-stationary opponents. Auton. Agent. Multi-Agent Syst. 31, 971\u20131002 (2017)","DOI":"10.1007\/s10458-016-9347-3"},{"key":"4_CR8","unstructured":"Hong, Z.W., Su, S.Y., Shann, T.Y., Chang, Y.H., Lee, C.Y.: A deep policy inference q-network for multi-agent systems. arXiv preprint arXiv:1712.07893 (2017)"},{"key":"4_CR9","first-page":"1179","volume":"33","author":"A Kumar","year":"2020","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative q-learning for offline reinforcement learning. Adv. Neural. Inf. Process. Syst. 33, 1179\u20131191 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/978-3-319-12601-2_10","volume-title":"Decision and Game Theory for Security","author":"A Laszka","year":"2014","unstructured":"Laszka, A., Horvath, G., Felegyhazi, M., Butty\u00e1n, L.: Flipthem: modeling targeted attacks with flipt, for multiple resources. In: Poovendran, R., Saad, W. (eds.) GameSec 2014. LNCS, vol. 8840, pp. 175\u2013194. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-12601-2_10"},{"key":"4_CR11","unstructured":"Li, L., Fayad, R., Taylor, A.: Cygil: a cyber gym for training autonomous agents over emulated network systems. arXiv preprint arXiv:2109.03331 (2021)"},{"key":"4_CR12","doi-asserted-by":"publisher","first-page":"2791","DOI":"10.1109\/TIFS.2021.3065504","volume":"16","author":"Z Liu","year":"2021","unstructured":"Liu, Z., Wang, L.: Flipit game model-based defense strategy against cyberattacks on SCADA systems considering insider assistance. IEEE Trans. Inf. Forensics Secur. 16, 2791\u20132804 (2021)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"12","key":"4_CR13","doi-asserted-by":"publisher","first-page":"7461","DOI":"10.1002\/int.22594","volume":"36","author":"Y Ma","year":"2021","unstructured":"Ma, Y., et al.: Opponent portrait for multiagent reinforcement learning in competitive environment. Int. J. Intell. Syst. 36(12), 7461\u20137474 (2021)","journal-title":"Int. J. Intell. Syst."},{"issue":"7540","key":"4_CR14","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"4_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1007\/978-3-030-32430-8_22","volume-title":"Decision and Game Theory for Security","author":"L Oakley","year":"2019","unstructured":"Oakley, L., Oprea, A.: $${\\sf QFlip}$$: an adaptive reinforcement learning strategy for the $${\\sf FlipIt}$$ security game. In: Alpcan, T., Vorobeychik, Y., Baras, J.S., D\u00e1n, G. (eds.) GameSec 2019. LNCS, vol. 11836, pp. 364\u2013384. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32430-8_22"},{"key":"4_CR16","unstructured":"Raileanu, R., Denton, E., Szlam, A., Fergus, R.: Modeling others using oneself in multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 4257\u20134266. PMLR (2018)"},{"key":"4_CR17","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015)"},{"issue":"7676","key":"4_CR18","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","journal-title":"Nature"},{"issue":"1","key":"4_CR19","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"4_CR20","unstructured":"Tang, Z., Zhu, Y., Zhao, D., Lucas, S.M.: Enhanced rolling horizon evolution algorithm with opponent model learning. IEEE Transactions on Games (2020)"},{"issue":"8","key":"4_CR21","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/S1353-4858(11)70086-1","volume":"2011","author":"C Tankard","year":"2011","unstructured":"Tankard, C.: Advanced persistent threats and how to monitor and deter them. Netw. Secur. 2011(8), 16\u201319 (2011)","journal-title":"Netw. Secur."},{"key":"4_CR22","unstructured":"Team, M.D.: CyberBattleSim (2021). https:\/\/github.com\/microsoft\/cyberbattlesim"},{"key":"4_CR23","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1007\/s00145-012-9134-5","volume":"26","author":"M Van Dijk","year":"2013","unstructured":"Van Dijk, M., Juels, A., Oprea, A., Rivest, R.L.: Flipit: the game of \u201cstealthy takeover.\u2019\u2019. J. Cryptol. 26, 655\u2013713 (2013)","journal-title":"J. Cryptol."},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30 (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"4_CR25","unstructured":"Wang, Z., Schaul, T., Hessel, M., Hasselt, H., Lanctot, M., Freitas, N.: Dueling network architectures for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1995\u20132003. PMLR (2016)"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Wu, Z., Li, K., Xu, H., Zang, Y., An, B., Xing, J.: L2e: learning to exploit your opponent. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2022)","DOI":"10.1109\/IJCNN55064.2022.9892077"},{"key":"4_CR27","doi-asserted-by":"publisher","first-page":"2026","DOI":"10.1109\/TIFS.2019.2955891","volume":"15","author":"R Zhang","year":"2019","unstructured":"Zhang, R., Zhu, Q.: Flipin: a game-theoretic cyber insurance framework for incentive-compatible cyber risk management of internet of things. IEEE Trans. Inf. Forensics Secur. 15, 2026\u20132041 (2019)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"10","key":"4_CR28","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3347-8","volume":"65","author":"J Zhu","year":"2022","unstructured":"Zhu, J., Wei, Y., Kang, Y., Jiang, X., Dullerud, G.E.: Adaptive deep reinforcement learning for non-stationary environments. Sci. Chin. Inf. Sci. 65(10), 202204 (2022)","journal-title":"Sci. Chin. Inf. Sci."}],"container-title":["Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","Collaborative Computing: Networking, Applications and Worksharing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-54528-3_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T07:21:34Z","timestamp":1708586494000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-54528-3_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031545276","9783031545283"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-54528-3_4","relation":{},"ISSN":["1867-8211","1867-822X"],"issn-type":[{"type":"print","value":"1867-8211"},{"type":"electronic","value":"1867-822X"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"23 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CollaborateCom","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Collaborative Computing: Networking, Applications and Worksharing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Corfu","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"colcom2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Cony +","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"176","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"72","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"41% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}