{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T00:02:26Z","timestamp":1778889746440,"version":"3.51.4"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T00:00:00Z","timestamp":1741132800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T00:00:00Z","timestamp":1741132800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Open Fund of State Key Laboratory of Satellite Navigation System and Equipment Technology","award":["CEPNT2022A01"],"award-info":[{"award-number":["CEPNT2022A01"]}]},{"name":"Open Fund of State Key Laboratory of Satellite Navigation System and Equipment Technology","award":["CEPNT2022A01"],"award-info":[{"award-number":["CEPNT2022A01"]}]},{"name":"Open Fund of State Key Laboratory of Satellite Navigation System and Equipment Technology","award":["CEPNT2022A01"],"award-info":[{"award-number":["CEPNT2022A01"]}]},{"name":"Open Fund of State Key Laboratory of Satellite Navigation System and Equipment Technology","award":["CEPNT2022A01"],"award-info":[{"award-number":["CEPNT2022A01"]}]},{"name":"Open Fund of State Key Laboratory of Satellite Navigation System and Equipment Technology","award":["CEPNT2022A01"],"award-info":[{"award-number":["CEPNT2022A01"]}]},{"name":"Open Fund of State Key Laboratory of Satellite Navigation System and Equipment Technology","award":["CEPNT2022A01"],"award-info":[{"award-number":["CEPNT2022A01"]}]},{"name":"Open Fund of State Key Laboratory of Satellite Navigation System and Equipment Technology","award":["CEPNT2022A01"],"award-info":[{"award-number":["CEPNT2022A01"]}]},{"name":"SongShan Laboratory Foundation","award":["No.YYJC062022017"],"award-info":[{"award-number":["No.YYJC062022017"]}]},{"name":"SongShan Laboratory Foundation","award":["No.YYJC062022017"],"award-info":[{"award-number":["No.YYJC062022017"]}]},{"name":"the Key Laboratory of Technology and Equipment of Tianjin Urban Air Transportation System","award":["No.TJKL-UAM-202305"],"award-info":[{"award-number":["No.TJKL-UAM-202305"]}]},{"name":"the Key Laboratory of Technology and Equipment of Tianjin Urban Air Transportation System","award":["No.TJKL-UAM-202305"],"award-info":[{"award-number":["No.TJKL-UAM-202305"]}]},{"name":"the Open Fund of State Key Laboratory of Dynamic Measurement Technology, North University of China","award":["2023-SYSJJ-04"],"award-info":[{"award-number":["2023-SYSJJ-04"]}]},{"name":"the Open Fund of State Key Laboratory of Dynamic Measurement Technology, North University of China","award":["2023-SYSJJ-04"],"award-info":[{"award-number":["2023-SYSJJ-04"]}]},{"name":"the Applied Basic Research Programs of Liaoning Province, China","award":["Nos.2022020502-JH2\/1013,2022JH2\/101300150"],"award-info":[{"award-number":["Nos.2022020502-JH2\/1013,2022JH2\/101300150"]}]},{"name":"the Applied Basic Research Programs of Liaoning Province, China","award":["Nos.2022020502-JH2\/1013,2022JH2\/101300150"],"award-info":[{"award-number":["Nos.2022020502-JH2\/1013,2022JH2\/101300150"]}]},{"DOI":"10.13039\/501100004750","name":"the Aeronautical Science Foundation of China","doi-asserted-by":"crossref","award":["20240055054001"],"award-info":[{"award-number":["20240055054001"]}],"id":[{"id":"10.13039\/501100004750","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004750","name":"the Aeronautical Science Foundation of China","doi-asserted-by":"crossref","award":["20240055054001"],"award-info":[{"award-number":["20240055054001"]}],"id":[{"id":"10.13039\/501100004750","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Agent Multi-Agent Syst"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s10458-025-09700-0","type":"journal-article","created":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T07:19:44Z","timestamp":1741159184000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Double mixing networks based monotonic value function decomposition algorithm for swarm intelligence in UAVs"],"prefix":"10.1007","volume":"39","author":[{"given":"Pingping","family":"Qu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenglong","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaotong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ershen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhui","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,5]]},"reference":[{"issue":"1","key":"9700_CR1","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1080\/09636412.2016.1134189","volume":"25","author":"A Gilli","year":"2016","unstructured":"Gilli, A., & Gilli, M. (2016). The diffusion of drone warfare? Industrial, organizational, and infrastructural constraints. Security Studies, 25(1), 50\u201384.","journal-title":"Security Studies"},{"issue":"1","key":"9700_CR2","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s11370-022-00452-4","volume":"16","author":"SAH Mohsan","year":"2023","unstructured":"Mohsan, S. A. H., Othman, N. Q. H., Li, Y., Alsharif, M. H., & Khan, M. A. (2023). Unmanned aerial vehicles (UAVs): Practical aspects, applications, open challenges, security issues, and future trends. Intelligent Service Robotics, 16(1), 109\u2013137.","journal-title":"Intelligent Service Robotics"},{"key":"9700_CR3","doi-asserted-by":"publisher","DOI":"10.4324\/9780203107218","volume-title":"Armed drones and the ethics of war: Military virtue in a post-heroic age","author":"C Enemark","year":"2013","unstructured":"Enemark, C. (2013). Armed drones and the ethics of war: Military virtue in a post-heroic age. Routledge."},{"issue":"12","key":"9700_CR4","doi-asserted-by":"publisher","first-page":"2802","DOI":"10.1016\/j.automatica.2009.09.025","volume":"45","author":"J Choi","year":"2009","unstructured":"Choi, J., Oh, S., & Horowitz, R. (2009). Distributed learning and cooperative control for multi-agent systems. Automatica, 45(12), 2802\u20132814.","journal-title":"Automatica"},{"issue":"8","key":"9700_CR5","doi-asserted-by":"publisher","first-page":"1799","DOI":"10.2514\/1.G003480","volume":"41","author":"X Wei","year":"2018","unstructured":"Wei, X., & Yang, J. (2018). Optimal strategies for multiple unmanned aerial vehicles in a pursuit\/evasion differential game. Journal of Guidance, Control, and Dynamics, 41(8), 1799\u20131806.","journal-title":"Journal of Guidance, Control, and Dynamics"},{"issue":"5","key":"9700_CR6","doi-asserted-by":"publisher","first-page":"4295","DOI":"10.1007\/s10462-022-10281-7","volume":"56","author":"J Tang","year":"2023","unstructured":"Tang, J., Duan, H., & Lao, S. (2023). Swarm intelligence algorithms for multiple unmanned aerial vehicles collaboration: A comprehensive review. Artificial Intelligence Review, 56(5), 4295\u20134327.","journal-title":"Artificial Intelligence Review"},{"key":"9700_CR7","doi-asserted-by":"crossref","unstructured":"Tang, Z., Wang, Y., Chen, Q., & Yang, X. (2020). Research on Target State Estimation and Terminal Guidance Algorithm in the Process of Multi-UAV Cooperative Attack. In 2020 5th International Conference on Automation, Control and Robotics Engineering (CACRE) (pp. 165-171). IEEE.","DOI":"10.1109\/CACRE50138.2020.9229963"},{"key":"9700_CR8","first-page":"8","volume":"5","author":"ZH Ismail","year":"2018","unstructured":"Ismail, Z. H., Sariff, N., & Hurtado, E. G. (2018). A survey and analysis of cooperative multi-agent robot systems: Challenges and directions. Applications of Mobile Robots, 5, 8\u201314.","journal-title":"Applications of Mobile Robots"},{"key":"9700_CR9","unstructured":"Mnih, V. (2013). Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602."},{"issue":"6419","key":"9700_CR10","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., Guez, A., Lanctot, M., Sifre, L., Kumaran, D., Graepel, T., & Hassabis, D. (2018). A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science, 362(6419), 1140\u20131144.","journal-title":"Science"},{"issue":"1","key":"9700_CR11","first-page":"10","volume":"49","author":"E Wang","year":"2023","unstructured":"Wang, E., Guo, J., Hong, C., & Shang, X. (2023). Cooperative confrontation model of UAV swarm with random spatial networks. Journal of Beijing University of Aeronautics and Astronautics, 49(1), 10\u201316.","journal-title":"Journal of Beijing University of Aeronautics and Astronautics"},{"issue":"6","key":"9700_CR12","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.cja.2024.03.030","volume":"37","author":"E Wang","year":"2024","unstructured":"Wang, E., Liu, F., Hong, C., Guo, J., Zhao, L., Xue, J., & He, N. (2024). MADRL-based UAV swarm non-cooperative game under incomplete information. Chinese Journal of Aeronautics, 37(6), 293\u2013306.","journal-title":"Chinese Journal of Aeronautics"},{"issue":"12","key":"9700_CR13","first-page":"2254","volume":"52","author":"E Wang","year":"2022","unstructured":"Wang, E., Liu, F., & Hong, C. (2022). MASAC-based confrontation game method of UAV clusters. China Science: Information Sciences, 52(12), 2254\u20132269.","journal-title":"China Science: Information Sciences"},{"issue":"4","key":"9700_CR14","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1287\/moor.27.4.819.297","volume":"27","author":"DS Bernstein","year":"2002","unstructured":"Bernstein, D. S., Givan, R., Immerman, N., & Zilberstein, S. (2002). The complexity of decentralized control of Markov decision processes. Mathematics of operations research, 27(4), 819\u2013840.","journal-title":"Mathematics of operations research"},{"key":"9700_CR15","unstructured":"Nair, R., Tambe, M., Roth, M., & Yokoo, M. (2004). Communications for improving policy computation in distributed POMDPs. In Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004. (pp. 1098-1105). IEEE."},{"key":"9700_CR16","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1613\/jair.2447","volume":"32","author":"FA Oliehoek","year":"2008","unstructured":"Oliehoek, F. A., Spaan, M. T., & Vlassis, N. (2008). Optimal and approximate Q-value functions for decentralized POMDPs. Journal of Artificial Intelligence Research, 32, 289\u2013353.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"9700_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8","volume-title":"A concise introduction to decentralized POMDPs","author":"FA Oliehoek","year":"2016","unstructured":"Oliehoek, F. A., & Amato, C. (2016). A concise introduction to decentralized POMDPs. Springer International Publishing. https:\/\/doi.org\/10.1007\/978-3-319-28929-8"},{"issue":"18","key":"9700_CR18","doi-asserted-by":"publisher","first-page":"17037","DOI":"10.1007\/s11071-023-08725-y","volume":"111","author":"A De Marco","year":"2023","unstructured":"De Marco, A., D\u2019Onza, P. M., & Manfredi, S. (2023). A deep reinforcement learning control approach for high-performance aircraft. Nonlinear Dynamics, 111(18), 17037\u201317077.","journal-title":"Nonlinear Dynamics"},{"issue":"7540","key":"9700_CR19","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, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., & Hassabis, D. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529\u2013533.","journal-title":"Nature"},{"key":"9700_CR20","unstructured":"Wang, Z., Schaul, T., Hessel, M., Hasselt, H., Lanctot, M., & Freitas, N. (2016). Dueling network architectures for deep reinforcement learning. In International Conference on Machine Learning (pp. 1995-2003). ACM."},{"key":"9700_CR21","unstructured":"Sunehag, P., Lever, G., Gruslys, A., Czarnecki, W. M., Zambaldi, V., Jaderberg, M., Lanctot, M.,Sonnerat, N.,Leibo, JZ., Tuyls,K., & Graepel, T. (2017). Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296."},{"key":"9700_CR22","unstructured":"Son, K., Kim, D., Kang, W. J., Hostallero, D. E., & Yi, Y. (2019). Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning. In International Conference on Machine Learning (pp. 5887-5896). ACM."},{"issue":"178","key":"9700_CR23","first-page":"1","volume":"21","author":"T Rashid","year":"2020","unstructured":"Rashid, T., Samvelyan, M., De Witt, C. S., Farquhar, G., Foerster, J., & Whiteson, S. (2020). Monotonic value function factorisation for deep multi-agent reinforcement learning. Journal of Machine Learning Research, 21(178), 1\u201351.","journal-title":"Journal of Machine Learning Research"},{"key":"9700_CR24","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347."},{"key":"9700_CR25","unstructured":"Christodoulou, P. (2019). Soft actor-critic for discrete action settings. arXiv preprint arXiv:1910.07207."},{"key":"9700_CR26","unstructured":"Lowe, R., Wu, Y. I., Tamar, A., Harb, J., Pieter Abbeel, O., & Mordatch, I. (2017). Multi-agent actor-critic for mixed cooperative-competitive environments. In Proceedings of the 31st International Conference on Neural Information Processing Systems (pp. 6382-6393). NIPS."},{"key":"9700_CR27","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, No. 1).","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"9700_CR28","doi-asserted-by":"crossref","unstructured":"Tan, M. (1993). Multi-agent reinforcement learning: Independent vs. cooperative agents. In Proceedings of the 10th International Conference on Machine Learning (pp. 330-337).","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"9700_CR29","unstructured":"Hausknecht, M.J., & Stone, P. (2015). Deep Recurrent Q-Learning for Partially Observable MDPs. arXiv preprint arXiv:1507.06527."},{"key":"9700_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, K., Yang, Z., & Basar, T. (2021). Multi-agent reinforcement learning: A selective overview of theories and algorithms. Handbook of reinforcement learning and control, 321-384.","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"9700_CR31","first-page":"15757","volume":"35","author":"H Zhou","year":"2022","unstructured":"Zhou, H., Lan, T., & Aggarwal, V. (2022). Pac: Assisted value factorization with counterfactual predictions in multi-agent reinforcement learning. Advances in Neural Information Processing Systems, 35, 15757\u201315769.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"9700_CR32","unstructured":"Wang, J., Ren, Z., Liu, T., Yu, Y., & Zhang, C. (2020). Qplex: Duplex dueling multi-agent q-learning. arXiv preprint arXiv:2008.01062."},{"key":"9700_CR33","unstructured":"Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2015). Gated feedback recurrent neural networks. In International conference on machine learning (pp. 2067-2075). PMLR."},{"key":"9700_CR34","unstructured":"Lim, H. D., & Lee, D. (2023). Temporal Difference Learning with Experience Replay. arXiv preprint arXiv:2306.09746."},{"key":"9700_CR35","unstructured":"Andrychowicz, M., Wolski, F., Ray, A., Schneider, J., Fong, R., Welinder, P., McGrew, B.,Tobin, J., Pieter Abbeel, O., & Zaremba, W. (2017). Hindsight experience replay. In Proceedings of the 31st Annual International Conference on Machine Learning, (pp. 5055-5065). ACM."},{"issue":"5","key":"9700_CR36","doi-asserted-by":"publisher","first-page":"1641","DOI":"10.2514\/1.46815","volume":"33","author":"JS McGrew","year":"2010","unstructured":"McGrew, J. S., How, J. P., Williams, B., & Roy, N. (2010). Air-combat strategy using approximate dynamic programming. Journal of guidance, control, and dynamics, 33(5), 1641\u20131654.","journal-title":"Journal of guidance, control, and dynamics"}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-025-09700-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10458-025-09700-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-025-09700-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T03:53:45Z","timestamp":1751860425000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10458-025-09700-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,5]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["9700"],"URL":"https:\/\/doi.org\/10.1007\/s10458-025-09700-0","relation":{},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"value":"1387-2532","type":"print"},{"value":"1573-7454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,5]]},"assertion":[{"value":"17 February 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 March 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"16"}}