{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T19:21:37Z","timestamp":1782588097267,"version":"3.54.5"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T00:00:00Z","timestamp":1721779200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T00:00:00Z","timestamp":1721779200000},"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":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s11432-023-4088-2","type":"journal-article","created":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T19:03:22Z","timestamp":1722020602000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["UAV swarm air combat maneuver decision-making method based on multi-agent reinforcement learning and transferring"],"prefix":"10.1007","volume":"67","author":[{"given":"Zhiqiang","family":"Zheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibin","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,24]]},"reference":[{"key":"4088_CR1","doi-asserted-by":"publisher","first-page":"2350004","DOI":"10.1142\/S2737480723500048","volume":"03","author":"S Fan","year":"2023","unstructured":"Fan S, Liu H H T. Multi-UAV cooperative hunting in cluttered environments considering downwash effects. Guid Navigat Control, 2023, 03: 2350004","journal-title":"Guid Navigat Control"},{"key":"4088_CR2","doi-asserted-by":"publisher","first-page":"111516","DOI":"10.1016\/j.automatica.2024.111516","volume":"162","author":"L Kong","year":"2024","unstructured":"Kong L, Reis J, He W, et al. On dynamic performance control for a quadrotor-slung-load system with unknown load mass. Automatica, 2024, 162: 111516","journal-title":"Automatica"},{"key":"4088_CR3","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1016\/j.dt.2023.02.007","volume":"31","author":"S Li","year":"2024","unstructured":"Li S, Shao X, Zhang W, et al. Distributed multicircular circumnavigation control for UAVs with desired angular spacing. Defence Tech, 2024, 31: 429\u2013446","journal-title":"Defence Tech"},{"key":"4088_CR4","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1109\/TMECH.2023.3282782","volume":"29","author":"L Kong","year":"2024","unstructured":"Kong L, Reis J, He W, et al. Experimental validation of a robust prescribed performance nonlinear controller for an unmanned aerial vehicle with unknown mass. IEEE ASME Trans Mechatron, 2024, 29: 301\u2013312","journal-title":"IEEE ASME Trans Mechatron"},{"key":"4088_CR5","doi-asserted-by":"publisher","first-page":"106358","DOI":"10.1016\/j.engappai.2023.106358","volume":"123","author":"F Jiang","year":"2023","unstructured":"Jiang F, Xu M, Li Y, et al. Short-range air combat maneuver decision of UAV swarm based on multi-agent transformer introducing virtual objects. Eng Appl Artif Intell, 2023, 123: 106358","journal-title":"Eng Appl Artif Intell"},{"key":"4088_CR6","doi-asserted-by":"publisher","first-page":"5943","DOI":"10.1177\/0954410019889447","volume":"233","author":"Y Q Dong","year":"2019","unstructured":"Dong Y Q, Ai J L, Liu J Q. Guidance and control for own aircraft in the autonomous air combat: a historical review and future prospects. Proc Inst Mech Eng Part G J Aero Eng, 2019, 233: 5943\u20135991","journal-title":"Proc Inst Mech Eng Part G J Aero Eng"},{"key":"4088_CR7","doi-asserted-by":"publisher","first-page":"104112","DOI":"10.1016\/j.engappai.2020.104112","volume":"98","author":"Z Sun","year":"2021","unstructured":"Sun Z, Piao H, Yang Z, et al. Multi-agent hierarchical policy gradient for air combat tactics emergence via self-play. Eng Appl Artif Intelligence, 2021, 98: 104112","journal-title":"Eng Appl Artif Intelligence"},{"key":"4088_CR8","doi-asserted-by":"crossref","unstructured":"Kong W R, Zhou D Y, Zhang K, et al. Air combat autonomous maneuver decision for one-on-one within visual range engagement base on robust multi-agent reinforcement learning. In: Proceedings of the 16th International Conference on Control & Automation (ICCA), Singapore, 2020. 506\u2013512","DOI":"10.1109\/ICCA51439.2020.9264567"},{"key":"4088_CR9","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1109\/ACCESS.2019.2961426","volume":"8","author":"Q Yang","year":"2019","unstructured":"Yang Q, Zhang J, Shi G, et al. Maneuver decision of UAV in short-range air combat based on deep reinforcement learning. IEEE Access, 2019, 8: 363\u2013378","journal-title":"IEEE Access"},{"key":"4088_CR10","doi-asserted-by":"publisher","first-page":"401","DOI":"10.3390\/aerospace10050401","volume":"10","author":"L Wang","year":"2023","unstructured":"Wang L, Wang J, Liu H, et al. Decision-making strategies for close-range air combat based on reinforcement learning with variable-scale actions. Aerospace, 2023, 10: 401","journal-title":"Aerospace"},{"key":"4088_CR11","doi-asserted-by":"publisher","first-page":"574","DOI":"10.3390\/aerospace10070574","volume":"10","author":"S Li","year":"2023","unstructured":"Li S, Wang Y, Zhou Y, et al. Multi-UAV cooperative air combat decision-making based on multi-agent double-soft actor-critic. Aerospace, 2023, 10: 574","journal-title":"Aerospace"},{"key":"4088_CR12","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1109\/JAS.2015.7032901","volume":"2","author":"H Duan","year":"2015","unstructured":"Duan H, Li P, Yu Y. A predator-prey particle swarm optimization approach to multiple UCAV air combat modeled by dynamic game theory. IEEE CAA J Autom Sin, 2015, 2: 11\u201318","journal-title":"IEEE CAA J Autom Sin"},{"key":"4088_CR13","doi-asserted-by":"publisher","first-page":"86","DOI":"10.21629\/JSEE.2018.01.09","volume":"29","author":"C Huang","year":"2018","unstructured":"Huang C, Dong K, Huang H, et al. Autonomous air combat maneuver decision using Bayesian inference and moving horizon optimization. J Syst Eng Electron, 2018, 29: 86\u201397","journal-title":"J Syst Eng Electron"},{"key":"4088_CR14","doi-asserted-by":"publisher","first-page":"102013","DOI":"10.1088\/1742-6596\/2478\/10\/102013","volume":"2478","author":"L Liu","year":"2023","unstructured":"Liu L, Zheng Y, Lu X, et al. Research on individual performance index of air cluster combat aircraft based on differential game theory. J Phys-Conf Ser, 2023, 2478: 102013","journal-title":"J Phys-Conf Ser"},{"key":"4088_CR15","doi-asserted-by":"crossref","unstructured":"Liu Y P, Gao X, Shi J X, et al. Research on decision-making method of air combat embedded training based on extended influence diagram. In: Proceedings of Advances in Guidance, Navigation and Control. Lecture Notes in Electrical Engineering, Singapore, 2021","DOI":"10.1007\/978-981-15-8155-7_375"},{"key":"4088_CR16","doi-asserted-by":"publisher","first-page":"1421","DOI":"10.23919\/JSEE.2021.000121","volume":"32","author":"Z Jiandong","year":"2021","unstructured":"Jiandong Z, Qiming Y, Guoqing S, et al. UAV cooperative air combat maneuver decision based on multi-agent reinforcement learning. J Syst Eng Electron, 2021, 32: 1421\u20131438","journal-title":"J Syst Eng Electron"},{"key":"4088_CR17","doi-asserted-by":"publisher","first-page":"1697","DOI":"10.1016\/j.dt.2021.09.014","volume":"18","author":"Y Li","year":"2022","unstructured":"Li Y, Shi J, Jiang W, et al. Autonomous maneuver decision-making for a UCAV in short-range aerial combat based on an MS-DDQN algorithm. Defence Tech, 2022, 18: 1697\u20131714","journal-title":"Defence Tech"},{"key":"4088_CR18","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1016\/j.dt.2023.08.019","volume":"34","author":"J Zhu","year":"2024","unstructured":"Zhu J, Kuang M, Zhou W, et al. Mastering air combat game with deep reinforcement learning. Defence Tech, 2024, 34: 295\u2013312","journal-title":"Defence Tech"},{"key":"4088_CR19","doi-asserted-by":"publisher","first-page":"2350007","DOI":"10.1142\/S2737480723500073","volume":"03","author":"X Yuan","year":"2023","unstructured":"Yuan X, Wang H, Yu W. A weighted mean field reinforcement learning algorithm for large-scale multi-agent collaboration. Guid Navigat Control, 2023, 03: 2350007","journal-title":"Guid Navigat Control"},{"key":"4088_CR20","doi-asserted-by":"publisher","first-page":"170201","DOI":"10.1007\/s11432-022-3796-2","volume":"66","author":"J N Li","year":"2023","unstructured":"Li J N, Nie H, Chai T, et al. Reinforcement learning for optimal tracking of large-scale systems with multitime scales. Sci China Inf Sci, 2023, 66: 170201","journal-title":"Sci China Inf Sci"},{"key":"4088_CR21","doi-asserted-by":"publisher","first-page":"4458","DOI":"10.1038\/s41598-024-54938-5","volume":"14","author":"H Wang","year":"2024","unstructured":"Wang H, Wang J. Enhancing multi-UAV air combat decision making via hierarchical reinforcement learning. Sci Rep, 2024, 14: 4458","journal-title":"Sci Rep"},{"key":"4088_CR22","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.dt.2023.11.013","volume":"35","author":"D Luo","year":"2024","unstructured":"Luo D, Fan Z, Yang Z, et al. Multi-UAV cooperative maneuver decision-making for pursuit-evasion using improved MADRL. Defence Tech, 2024, 35: 187\u2013197","journal-title":"Defence Tech"},{"key":"4088_CR23","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.comcom.2023.01.009","volume":"200","author":"Z Wang","year":"2023","unstructured":"Wang Z, Guo Y, Li N, et al. Autonomous collaborative combat strategy of unmanned system group in continuous dynamic environment based on PD-MADDPG. Comput Commun, 2023, 200: 182\u2013204","journal-title":"Comput Commun"},{"key":"4088_CR24","doi-asserted-by":"publisher","first-page":"104767","DOI":"10.1016\/j.engappai.2022.104767","volume":"111","author":"D Hu","year":"2022","unstructured":"Hu D, Yang R, Zhang Y, et al. Aerial combat maneuvering policy learning based on confrontation demonstrations and dynamic quality replay. Eng Appl Artif Intell, 2022, 111: 104767","journal-title":"Eng Appl Artif Intell"},{"key":"4088_CR25","doi-asserted-by":"crossref","unstructured":"Austin F, Carbone G, Falco M, et al. Automated maneuvering decisions for air-to-air combat. In: Proceedings of Guidance, Navigation and Control Conference, Monterey, 1987","DOI":"10.2514\/6.1987-2393"},{"key":"4088_CR26","first-page":"1553","volume":"42","author":"A W Yang","year":"2021","unstructured":"Yang A W, Li Z W, Li B, et al. Air combat situation assessment based on dynamic variable weight. Acta Armamentarii, 2021, 42: 1553\u20131563","journal-title":"Acta Armamentarii"},{"key":"4088_CR27","doi-asserted-by":"publisher","first-page":"166","DOI":"10.3390\/drones6070166","volume":"6","author":"G Zhan","year":"2022","unstructured":"Zhan G, Zhang X, Li Z, et al. Multiple-UAV reinforcement learning algorithm based on improved PPO in ray framework. Drones, 2022, 6: 166","journal-title":"Drones"},{"key":"4088_CR28","unstructured":"Yu C, Velu A, Vinitsky E, et al. The surprising effectiveness of PPO in cooperative, multi-agent games. 2021. ArXiv:2103.01955"},{"key":"4088_CR29","unstructured":"Schulman J, Wolski F, Dhariwal P, at al. Proximal policy optimization algorithms. 2017. ArXiv:1707.06347"},{"key":"4088_CR30","doi-asserted-by":"publisher","first-page":"132202","DOI":"10.1007\/s11432-022-3543-4","volume":"66","author":"J W Zhu","year":"2023","unstructured":"Zhu J W, Zhang H, Zhao S B, et al. Multi-constrained intelligent gliding guidance via optimal control and DQN. Sci China Inf Sci, 2023, 66: 132202","journal-title":"Sci China Inf Sci"},{"key":"4088_CR31","doi-asserted-by":"crossref","unstructured":"Li L T, Zhou Z M, Chai J J, et al. Learning continuous 3-DoF air-to-air close-in combat strategy using proximal policy optimization. In: Proceedings of IEEE Conference on Games (CoG), Beijing, 2022. 616\u2013619","DOI":"10.1109\/CoG51982.2022.9893690"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-023-4088-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-023-4088-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-023-4088-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T19:39:32Z","timestamp":1758310772000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-023-4088-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,24]]},"references-count":31,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["4088"],"URL":"https:\/\/doi.org\/10.1007\/s11432-023-4088-2","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,24]]},"assertion":[{"value":"28 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 March 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"180204"}}