{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T12:03:39Z","timestamp":1779710619957,"version":"3.53.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"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":["J Ambient Intell Human Comput"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1007\/s12652-026-05076-5","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T14:45:50Z","timestamp":1776091550000},"page":"851-862","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Boosting multi-agent reinforcement learning with pruned prioritized experience replay and collaborative learning. Case study: intrusion detection system"],"prefix":"10.1007","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8582-6092","authenticated-orcid":false,"given":"Faten","family":"Louati","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farah Barika","family":"Ktata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ikram","family":"Amous","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"issue":"7540","key":"5076_CR1","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"5076_CR2","unstructured":"Papoudakis G, Christianos F, Rahman A, Albrecht SV (2019) Dealing with non-stationarity in multi-agent deep reinforcement learning. arXiv preprint arXiv:1906.04737"},{"key":"5076_CR3","doi-asserted-by":"crossref","unstructured":"Littman ML (1994) Markov games as a framework for multi-agent reinforcement learning. In: Machine learning proceedings. Elsevier, pp 157\u2013163","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"5076_CR4","unstructured":"Schaul T, Quan J, Antonoglou I, Silver D (2015) Prioritized experience replay. arXiv preprint arXiv:1511.05952"},{"key":"5076_CR5","unstructured":"Anderson J (1980) Computer security threat monitoring and surveillance. James P. Anderson Company, Fort Washington, Tech. Rep., 02"},{"key":"5076_CR6","unstructured":"Chu T, Chinchali S, Katti S (2020) Multi-agent reinforcement learning for networked system control. In: International Conference on Learning Representations, [Online]. https:\/\/openreview.net\/forum?id=Syx7A3NFvH"},{"key":"5076_CR7","unstructured":"Zhang K, Yang Z, Liu H, Zhang T, Basar T (2018) Fully decentralized multi-agent reinforcement learning with networked agents. In: Proceedings of the 35th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research, J.\u00a0Dy and A.\u00a0Krause, Eds., vol 80. PMLR, 10\u201315, pp 5872\u20135881. [Online]. http:\/\/proceedings.mlr.press\/v80\/zhang18n.html"},{"key":"5076_CR8","unstructured":"Jiang J, Lu Z (2018) Learning attentional communication for multi-agent cooperation. In: NeurIPS"},{"key":"5076_CR9","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.comnet.2019.05.013","volume":"159","author":"G Caminero Fern\u00e1ndez","year":"2019","unstructured":"Caminero Fern\u00e1ndez G, Lopez-Martin M, Carro B (2019) Adversarial environment reinforcement learning algorithm for intrusion detection. Comput Netw 159:96\u2013109","journal-title":"Comput Netw"},{"key":"5076_CR10","doi-asserted-by":"crossref","unstructured":"Gruver N, Song J, Kochenderfer MJ, Ermon S (2020) Multi-agent adversarial inverse reinforcement learning with latent variables. In: AAMAS","DOI":"10.65109\/CSNK6237"},{"key":"5076_CR11","unstructured":"Yu L, Song J, Ermon S (2019) Multi-agent adversarial inverse reinforcement learning, 07"},{"key":"5076_CR12","unstructured":"Lowe R, Wu Y, Tamar A, Harb J, Abbeel P, Mordatch I (2020) Multi-agent actor-critic for mixed cooperative-competitive environments"},{"key":"5076_CR13","doi-asserted-by":"crossref","unstructured":"Liang C, Shanmugam B, Azam S, Jonkman M, Boer FD, Narayansamy G (2019) Intrusion detection system for internet of things based on a machine learning approach. In: 2019 International conference on vision towards emerging trends in communication and networking (ViTECoN), pp 1\u20136","DOI":"10.1109\/ViTECoN.2019.8899448"},{"key":"5076_CR14","volume":"61","author":"K Sethi","year":"2021","unstructured":"Sethi K, Madhav YV, Kumar R, Bera P (2021) Attention based multi-agent intrusion detection systems using reinforcement learning. J Inf Secur Appl 61:102923","journal-title":"J Inf Secur Appl"},{"key":"5076_CR15","doi-asserted-by":"crossref","unstructured":"Shi G, He G (2021) Collaborative multi-agent reinforcement learning for intrusion detection. In: 2021 7th IEEE international conference on network intelligence and digital content (IC-NIDC). IEEE, pp 245\u2013249","DOI":"10.1109\/IC-NIDC54101.2021.9660402"},{"key":"5076_CR16","doi-asserted-by":"crossref","unstructured":"Gupta J, Egorov M, Kochenderfer M (2017) Cooperative multi-agent control using deep reinforcement learning 11:66\u201383","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"5076_CR17","unstructured":"Kong X, Xin B, Liu F, Wang Y (2017) Revisiting the master-slave architecture in multi-agent deep reinforcement learning, 12"},{"key":"5076_CR18","doi-asserted-by":"crossref","unstructured":"Sunehag P, Lever G, Gruslys A, Czarnecki WM, Zambaldi V, Jaderberg M, Lanctot M, Sonnerat N, Leibo JZ, Tuyls K et\u00a0al (2017) Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296,","DOI":"10.65109\/JSRC7365"},{"issue":"1","key":"5076_CR19","first-page":"7234","volume":"21","author":"T Rashid","year":"2020","unstructured":"Rashid T, Samvelyan M, De Witt CS, Farquhar G, Foerster J, Whiteson S (2020) Monotonic value function factorisation for deep multi-agent reinforcement learning. J Mach Learn Res 21(1):7234\u20137284","journal-title":"J Mach Learn Res"},{"key":"5076_CR20","unstructured":"Son K, Kim D, Kang WJ, Hostallero DE, Yi Y (2019) Qtran: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: International conference on machine learning. PMLR, pp 5887\u20135896"},{"key":"5076_CR21","doi-asserted-by":"crossref","unstructured":"Fuji T, Ito K, Matsumoto K, Yano K (2018) Deep multi-agent reinforcement learning using dnn-weight evolution to optimize supply chain performance. In: Hawaii international conference on system sciences","DOI":"10.24251\/HICSS.2018.157"},{"key":"5076_CR22","doi-asserted-by":"crossref","unstructured":"Foerster J, Farquhar G, Afouras T, Nardelli N, Whiteson S (2018) Counterfactual multi-agent policy gradients. In: Proceedings of the AAAI conference on artificial intelligence, vol 32(1)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"5076_CR23","unstructured":"Lowe R, Wu YI, Tamar A, Harb J, Pieter\u00a0Abbeel O, Mordatch I (2017) Multi-agent actor-critic for mixed cooperative-competitive environments. Adv Neural Inf Process Syst 30"},{"key":"5076_CR24","doi-asserted-by":"crossref","unstructured":"Louati F, Ktata FB, Amous I (2024) An intelligent security system using enhanced anomaly-based detection scheme. Comput J","DOI":"10.1093\/comjnl\/bxae008"},{"key":"5076_CR25","doi-asserted-by":"crossref","unstructured":"Louati F, Ktata FB, Amous I (2024) Big-ids: a decentralized multi agent reinforcement learning approach for distributed intrusion detection in big data networks. Cluster Comput","DOI":"10.1007\/s10586-024-04306-9"},{"key":"5076_CR26","first-page":"10707","volume":"33","author":"F Christianos","year":"2020","unstructured":"Christianos F, Sch\u00e4fer L, Albrecht S (2020) Shared experience actor-critic for multi-agent reinforcement learning. Adv Neural Inf Process Syst 33:10707","journal-title":"Adv Neural Inf Process Syst"},{"issue":"4","key":"5076_CR27","doi-asserted-by":"publisher","first-page":"470","DOI":"10.3390\/e24040470","volume":"24","author":"D Shi","year":"2022","unstructured":"Shi D, Tong J, Liu Y, Fan W (2022) Knowledge reuse of multi-agent reinforcement learning in cooperative tasks. Entropy 24(4):470","journal-title":"Entropy"},{"key":"5076_CR28","unstructured":"Horgan D, Quan J, Budden D, Barth-Maron G, Hessel M, Van\u00a0Hasselt H, Silver D (2018) Distributed prioritized experience replay. arXiv preprint arXiv:1803.00933"},{"key":"5076_CR29","doi-asserted-by":"crossref","unstructured":"Gerstgrasser M, Danino T, Keren S (2023) Selectively sharing experiences improves multi-agent reinforcement learning. arXiv preprint arXiv:2311.00865","DOI":"10.65109\/YQSX9164"},{"key":"5076_CR30","unstructured":"Foerster JN, Assael YM, de\u00a0Freitas N, Whiteson S (2016) Learning to communicate to solve riddles with deep distributed recurrent q-networks. arXiv preprint arXiv:1602.02672"},{"key":"5076_CR31","unstructured":"Sukhbaatar S, Fergus R et\u00a0al (2016) Learning multiagent communication with backpropagation. Adv Neural Inf Process Syst 29"},{"key":"5076_CR32","unstructured":"Singh A, Jain T, Sukhbaatar S (2018) Learning when to communicate at scale in multiagent cooperative and competitive tasks. arXiv preprint arXiv:1812.09755"},{"key":"5076_CR33","unstructured":"Foerster J, Assael IA, De\u00a0Freitas N, Whiteson S (2016) Learning to communicate with deep multi-agent reinforcement learning. Adv Neural Inf Process Syst 29"},{"key":"5076_CR34","doi-asserted-by":"crossref","unstructured":"Mordatch I, Abbeel P (2018) Emergence of grounded compositional language in multi-agent populations. In: Proceedings of the AAAI conference on artificial intelligence, vol 32(1)","DOI":"10.1609\/aaai.v32i1.11492"},{"issue":"1","key":"5076_CR35","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/s10207-022-00634-2","volume":"22","author":"S Mohamed","year":"2023","unstructured":"Mohamed S, Ejbali R (2023) Deep sarsa-based reinforcement learning approach for anomaly network intrusion detection system. Int J Inf Secur 22(1):235\u2013247","journal-title":"Int J Inf Secur"},{"issue":"28","key":"5076_CR36","doi-asserted-by":"publisher","first-page":"71559","DOI":"10.1007\/s11042-024-18289-7","volume":"83","author":"V Shakya","year":"2024","unstructured":"Shakya V, Choudhary J, Singh DP (2024) Irada: Integrated reinforcement learning and deep learning algorithm for attack detection in wireless sensor networks. Multimedia Tools Appl 83(28):71559\u201371578","journal-title":"Multimedia Tools Appl"},{"key":"5076_CR37","doi-asserted-by":"crossref","unstructured":"Sujatha V, Prasanna KL, Niharika K, Charishma V Sai KB (20203) Network intrusion detection using deep reinforcement learning. In: 2023 7th International conference on computing methodologies and communication (ICCMC), pp 1146\u20131150","DOI":"10.1109\/ICCMC56507.2023.10083673"},{"key":"5076_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2024.103786","volume":"140","author":"C Rookard","year":"2024","unstructured":"Rookard C, Khojandi A (2024) Rriot: recurrent reinforcement learning for cyber threat detection on iot devices. Comput Secur 140:103786","journal-title":"Comput Secur"},{"key":"5076_CR39","doi-asserted-by":"crossref","unstructured":"Tareq I, Elbagoury BM, El-Regaily SA, El-Horbaty E-SM (2024) Deep reinforcement learning approach for cyberattack detection. Int J Online Biomed Eng 20(5)","DOI":"10.3991\/ijoe.v20i05.48229"},{"key":"5076_CR40","doi-asserted-by":"crossref","unstructured":"Suwannalai E, Polprasert C (2020) Network intrusion detection systems using adversarial reinforcement learning with deep q-network. In: 2020 18th International conference on ICT and knowledge engineering (ICT KE), pp 1\u20137","DOI":"10.1109\/ICTKE50349.2020.9289884"},{"issue":"2","key":"5076_CR41","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1109\/TNSE.2020.3004312","volume":"8","author":"X Ma","year":"2021","unstructured":"Ma X, Shi W (2021) Aesmote: adversarial reinforcement learning with smote for anomaly detection. IEEE Trans Netw Sci Eng 8(2):943\u2013956","journal-title":"IEEE Trans Netw Sci Eng"}],"container-title":["Journal of Ambient Intelligence and Humanized Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-026-05076-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12652-026-05076-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-026-05076-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T11:29:23Z","timestamp":1779708563000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12652-026-05076-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":41,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["5076"],"URL":"https:\/\/doi.org\/10.1007\/s12652-026-05076-5","relation":{},"ISSN":["1868-5137","1868-5145"],"issn-type":[{"value":"1868-5137","type":"print"},{"value":"1868-5145","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"24 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}