{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T09:15:49Z","timestamp":1771233349863,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T00:00:00Z","timestamp":1768262400000},"content-version":"vor","delay-in-days":35,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s40747-025-02189-w","type":"journal-article","created":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T18:47:07Z","timestamp":1765306027000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive exploration and temporal attention in reinforcement learning for autonomous air combat decision making"],"prefix":"10.1007","volume":"12","author":[{"given":"Xiang","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junzhe","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaojie","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenghong","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueyun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,9]]},"reference":[{"issue":"20","key":"2189_CR1","first-page":"1","volume":"4","author":"P Layton","year":"2021","unstructured":"Layton P (2021) Fighting artificial intelligence battles: operational concepts for future ai-enabled wars. Network 4(20):1\u2013100","journal-title":"Network"},{"issue":"11","key":"2189_CR2","doi-asserted-by":"publisher","first-page":"5005","DOI":"10.1109\/TNNLS.2019.2955400","volume":"31","author":"R Chai","year":"2019","unstructured":"Chai R, Tsourdos A, Savvaris A et al (2019) Six-DOF spacecraft optimal trajectory planning and real-time attitude control: a deep neural network-based approach [J]. IEEE Trans Neural Netw Learn Syst 31(11):5005\u20135013","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"8","key":"2189_CR3","doi-asserted-by":"publisher","first-page":"6904","DOI":"10.1109\/TIE.2019.2939934","volume":"67","author":"R Chai","year":"2019","unstructured":"Chai R, Tsourdos A, Savvaris A et al (2019) Real-time reentry trajectory planning of hypersonic vehicles: a two-step strategy incorporating fuzzy multiobjective transcription and deep neural network [J]. IEEE Trans Ind Electron 67(8):6904\u20136915","journal-title":"IEEE Trans Ind Electron"},{"issue":"9","key":"2189_CR4","doi-asserted-by":"publisher","first-page":"1639","DOI":"10.1109\/JAS.2022.105803","volume":"9","author":"W Ruan","year":"2022","unstructured":"Ruan W, Duan H, Deng Y (2022) Autonomous maneuver decisions via transfer learning pigeon-inspired optimization for UCAVs in dogfight engagements. IEEE CAA J Autom Sin 9(9):1639\u20131657","journal-title":"IEEE CAA J Autom Sin"},{"issue":"10","key":"2189_CR5","doi-asserted-by":"publisher","DOI":"10.1177\/1687814016674384","volume":"8","author":"Y Wang","year":"2016","unstructured":"Wang Y, Huang C, Tang C (2016) Research on unmanned combat aerial vehicle robust maneuvering decision under incomplete target information. Adv Mech Eng 8(10):1687814016674384","journal-title":"Adv Mech Eng"},{"key":"2189_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110561","volume":"145","author":"R Chai","year":"2022","unstructured":"Chai R, Tsourdos A, Gao H et al (2022) Attitude tracking control for reentry vehicles using centralised robust model predictive control. Automatica 145:110561","journal-title":"Automatica"},{"issue":"4","key":"2189_CR7","doi-asserted-by":"publisher","first-page":"4022","DOI":"10.1109\/TIE.2021.3076729","volume":"69","author":"R Chai","year":"2021","unstructured":"Chai R, Tsourdos A, Gao H et al (2021) Dual-loop tube-based robust model predictive attitude tracking control for spacecraft with system constraints and additive disturbances [J]. IEEE Trans Ind Electron 69(4):4022\u20134033","journal-title":"IEEE Trans Ind Electron"},{"issue":"6","key":"2189_CR8","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1016\/j.cja.2023.04.020","volume":"36","author":"XI Zhifei","year":"2023","unstructured":"Zhifei XI, Yue LYU, Yingxin KOU et al (2023) An online ensemble semi-supervised classification framework for air combat target maneuver recognition [J]. Chin J Aeronaut 36(6):340\u2013360","journal-title":"Chin J Aeronaut"},{"issue":"2","key":"2189_CR9","doi-asserted-by":"publisher","first-page":"498","DOI":"10.23919\/JSEE.2021.000042","volume":"32","author":"XI Zhifei","year":"2021","unstructured":"Zhifei XI, An XU, Yingxin K et al (2021) Target maneuver trajectory prediction based on RBF neural network optimized by hybrid algorithm [J]. J Syst Eng Electron 32(2):498\u2013516","journal-title":"J Syst Eng Electron"},{"key":"2189_CR10","doi-asserted-by":"publisher","first-page":"32282","DOI":"10.1109\/ACCESS.2021.3060426","volume":"9","author":"D Hu","year":"2021","unstructured":"Hu D, Yang R, Zuo J et al (2021) Application of deep reinforcement learning in maneuver planning of beyond-visual-range air combat. IEEE Access 9:32282\u201332297","journal-title":"IEEE Access"},{"key":"2189_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117448","volume":"203","author":"JB Crumpacker","year":"2022","unstructured":"Crumpacker JB, Robbins MJ, Jenkins PR (2022) An approximate dynamic programming approach for solving an air combat maneuvering problem. Expert Syst Appl 203:117448","journal-title":"Expert Syst Appl"},{"issue":"5","key":"2189_CR12","doi-asserted-by":"publisher","first-page":"1641","DOI":"10.2514\/1.46815","volume":"33","author":"JS McGrew","year":"2010","unstructured":"McGrew JS, How JP, Williams B et al (2010) Air-combat strategy using approximate dynamic programming. J Guid Control Dyn 33(5):1641\u20131654","journal-title":"J Guid Control Dyn"},{"issue":"18","key":"2189_CR13","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 PM, Manfredi S (2023) A deep reinforcement learning control approach for high-performance aircraft. Nonlinear Dyn 111(18):17037\u201317077","journal-title":"Nonlinear Dyn"},{"key":"2189_CR14","doi-asserted-by":"publisher","first-page":"107599","DOI":"10.1109\/ACCESS.2024.3437191","volume":"12","author":"M Abdelsattar","year":"2024","unstructured":"Abdelsattar M, Ismeil MA, Zayed MMAA et al (2024) Assessing machine learning approaches for photovoltaic energy prediction in sustainable energy systems. IEEE Access 12:107599\u2013107615","journal-title":"IEEE Access"},{"issue":"1","key":"2189_CR15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0317619","volume":"20","author":"M Abdelsattar","year":"2025","unstructured":"Abdelsattar M, A. Ismeil M, Menoufi K et al (2025) Evaluating machine learning and deep learning models for predicting wind turbine power output from environmental factors. PLoS ONE 20(1):e0317619","journal-title":"PLoS ONE"},{"issue":"7540","key":"2189_CR16","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 et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"2189_CR17","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins CJCH, Dayan P (1992) Q-learning. Mach Learn 8:279\u2013292","journal-title":"Mach Learn"},{"key":"2189_CR18","unstructured":"Fan J, Wang Z, Xie Y et al (2020) A theoretical analysis of deep Q-learning [C]. In: Learning for dynamics and control. PMLR, pp 486\u2013489"},{"key":"2189_CR19","unstructured":"Haarnoja T, Zhou A, Abbeel P et al (2018) Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor [C]. In: International conference on machine learning. Pmlr, pp 1861\u20131870"},{"key":"2189_CR20","unstructured":"Sutton R S, McAllester D, Singh S et al (1999) Policy gradient methods for reinforcement learning with function approximation [J]. In: Advances in neural information processing systems, 12"},{"key":"2189_CR21","unstructured":"Schulman J, Wolski F, Dhariwal P et al (2017) Proximal policy optimization algorithms [J]. arXiv preprint arXiv:1707.06347"},{"key":"2189_CR22","doi-asserted-by":"crossref","unstructured":"Gao Y, Li Y, Guo Z (2021) A Q-learning based UAV path planning method with awareness of risk avoidance [C]. In: 2021 China automation congress (CAC). IEEE, pp 669\u2013673","DOI":"10.1109\/CAC53003.2021.9728342"},{"key":"2189_CR23","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 (2019) Maneuver decision of UAV in short-range air combat based on deep reinforcement learning [J]. IEEE Access 8:363\u2013378","journal-title":"IEEE Access"},{"issue":"3","key":"2189_CR24","doi-asserted-by":"publisher","DOI":"10.3390\/aerospace12030265","volume":"12","author":"C Chen","year":"2025","unstructured":"Chen C, Song T, Mo L et al (2025) Autonomous dogfight decision-making for air combat based on reinforcement learning with automatic opponent sampling. Aerospace 12(3):265","journal-title":"Aerospace"},{"issue":"1","key":"2189_CR25","first-page":"3657814","volume":"2023","author":"Y Cao","year":"2023","unstructured":"Cao Y, Kou YX, Li ZW et al (2023) Autonomous maneuver decision of UCAV air combat based on double deep Q network algorithm and stochastic game theory [J]. Int J Aerospace Eng 2023(1):3657814","journal-title":"Int J Aerospace Eng"},{"key":"2189_CR26","doi-asserted-by":"publisher","first-page":"29064","DOI":"10.1109\/ACCESS.2020.2971780","volume":"8","author":"B Li","year":"2020","unstructured":"Li B, Wu Y (2020) Path planning for UAV ground target tracking via deep reinforcement learning. IEEE Access 8:29064\u201329074","journal-title":"IEEE Access"},{"key":"2189_CR27","doi-asserted-by":"crossref","unstructured":"Chen X, Diao D, Chen H et al (2023) The sufficiency of off-policyness and soft clipping: PPO is still insufficient according to an off-policy measure [C]. In: Proceedings of the AAAI conference on artificial intelligence, vol 37(6), pp 7078\u20137086","DOI":"10.1609\/aaai.v37i6.25864"},{"key":"2189_CR28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3419889","author":"H Wang","year":"2024","unstructured":"Wang H, Zhou Z, Jiang J et al (2024) Autonomous air combat maneuver decision-making based on PPO-BWDA. IEEE Access. https:\/\/doi.org\/10.1109\/ACCESS.2024.3419889","journal-title":"IEEE Access"},{"issue":"3","key":"2189_CR29","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1007\/s42405-024-00707-7","volume":"25","author":"C Zhang","year":"2024","unstructured":"Zhang C, Tao C, Xu Y et al (2024) Autonomous defense of unmanned aerial vehicles against missile attacks using a GRU-based PPO algorithm. Int J Aeronaut Space Sci 25(3):1034\u20131049","journal-title":"Int J Aeronaut Space Sci"},{"key":"2189_CR30","first-page":"17086","volume":"35","author":"J Hilton","year":"2022","unstructured":"Hilton J, Cobbe K, Schulman J (2022) Batch size-invariance for policy optimization. Adv Neural Inf Process Syst 35:17086\u201317098","journal-title":"Adv Neural Inf Process Syst"},{"issue":"1","key":"2189_CR31","first-page":"97","volume":"44","author":"Y Yin","year":"2022","unstructured":"Yin Y, Wang F, Wu K et al (2022) Research on air combat behavior decision-making method based on improved DDPG [J]. Command Control Simul 44(1):97\u2013102","journal-title":"Command Control Simul"},{"key":"2189_CR32","unstructured":"Fujimoto S, Hoof H, Meger D (2018) Addressing function approximation error in actor-critic methods [C]. In: International conference on machine learning. PMLR, pp 1587\u20131596"},{"issue":"05","key":"2189_CR33","first-page":"24","volume":"44","author":"B Li","year":"2022","unstructured":"Li B, Bai S, Meng B et al (2022) Autonomous air combat decision-making algorithm of UAVs based on SAC algorithm [J]. Command Control Simul 44(05):24\u201330","journal-title":"Command Control Simul"},{"key":"2189_CR34","doi-asserted-by":"crossref","unstructured":"Zhou H, Zhang S, Peng J et al (2021) In.former: beyond efficient transformer for long sequence time-series forecasting [C]. In: Proceedings of the AAAI conference on artificial intelligence, vol 35(12), pp 11106\u201311115","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"2189_CR35","unstructured":"Foret P, Kleiner A, Mobahi H et al (2020) Sharpness-aware minimization for efficiently improving generalization [J]. arXiv preprint arXiv:2010.01412"},{"key":"2189_CR36","unstructured":"Zhang M, Lucas J, Ba J et al (2019) Lookahead optimizer: k steps forward, 1 step back [J]. In: Advances in neural information processing systems, p 32"},{"issue":"1","key":"2189_CR37","first-page":"36","volume":"13","author":"AHK Alaboudy","year":"2023","unstructured":"Alaboudy AHK, Elbaset AA, Abdelsattar M (2023) A case study on the LVRT capability of an egyptian electrical grid linked to the Al-Zafarana wind park using series resistor. Int J Renew Energy Res (IJRER) 13(1):36\u201348","journal-title":"Int J Renew Energy Res (IJRER)"},{"issue":"26","key":"2189_CR38","doi-asserted-by":"publisher","first-page":"16251","DOI":"10.1007\/s00521-024-09902-9","volume":"36","author":"M Abdelsattar","year":"2024","unstructured":"Abdelsattar M, Mesalam A, Diab AAZ et al (2024) Optimal sizing of a proposed stand-alone hybrid energy system in a remote region of southwest Egypt applying different meta-heuristic algorithms. Neural Comput Appl 36(26):16251\u201316269","journal-title":"Neural Comput Appl"},{"key":"2189_CR39","doi-asserted-by":"crossref","unstructured":"Berndt J (2004) JSBSim: an open source flight dynamics model in C++[C]. In: AIAA modeling and simulation technologies conference and exhibit, p 4923","DOI":"10.2514\/6.2004-4923"}],"container-title":["Complex & Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-02189-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-025-02189-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-02189-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T08:23:50Z","timestamp":1771230230000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-025-02189-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":39,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2189"],"URL":"https:\/\/doi.org\/10.1007\/s40747-025-02189-w","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,9]]},"assertion":[{"value":"16 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 December 2025","order":3,"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"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"69"}}