{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T07:15:09Z","timestamp":1775891709231,"version":"3.50.1"},"reference-count":33,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["NSTC 111\\u20132923-E-006\\u2013\\u2013004 \\u2212MY3"],"award-info":[{"award-number":["NSTC 111\\u20132923-E-006\\u2013\\u2013004 \\u2212MY3"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["NSTC 113\\u20132218-E-006\\u2013\\u2013021"],"award-info":[{"award-number":["NSTC 113\\u20132218-E-006\\u2013\\u2013021"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Advanced Engineering Informatics"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1016\/j.aei.2025.103988","type":"journal-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T09:00:27Z","timestamp":1761382827000},"page":"103988","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"PC","title":["Physics-informed reinforcement learning for air-to-air F16 target aiming"],"prefix":"10.1016","volume":"69","author":[{"given":"Yi-Ho","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng-Huan","family":"Chiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4068-0632","authenticated-orcid":false,"given":"Chao-Chung","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.aei.2025.103988_b0005","unstructured":"A. F. Schools. \u201cThe Cost of Flight Training.\u201d https:\/\/americanflightschools.com\/learn-to-fly\/cost-of-flight-training\/ (accessed August 18, 2025)."},{"issue":"1","key":"10.1016\/j.aei.2025.103988_b0010","doi-asserted-by":"crossref","first-page":"22","DOI":"10.4103\/jmedsci.jmedsci_94_20","article-title":"Analysis of in-flight spatial disorientation among military pilots in Taiwan","volume":"41","author":"Tu","year":"2021","journal-title":"J. Med. Sci."},{"key":"10.1016\/j.aei.2025.103988_b0015","unstructured":"J. A. Tirpak. \u201cReforging Fighter Pilot Training.\u201d https:\/\/www.airforcemag.com\/article\/reforging-fighter-pilot-training\/ (accessed August 18, 2025)."},{"issue":"5","key":"10.1016\/j.aei.2025.103988_b0020","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.2514\/1.46815","article-title":"Air-combat strategy using approximate dynamic programming","volume":"33","author":"McGrew","year":"2010","journal-title":"J. Guid. Control Dynam."},{"issue":"16","key":"10.1016\/j.aei.2025.103988_b0025","doi-asserted-by":"crossref","first-page":"5943","DOI":"10.1177\/0954410019889447","article-title":"Guidance and control for own aircraft in the autonomous air combat: a historical review and future prospects","volume":"233","author":"Dong","year":"2019","journal-title":"Proc. Inst. Mech. Eng., G: J. Aerospace Eng."},{"issue":"1","key":"10.1016\/j.aei.2025.103988_b0030","first-page":"2167","article-title":"Genetic fuzzy based artificial intelligence for unmanned combat aerial vehicle control in simulated air combat missions","volume":"6","author":"Ernest","year":"2016","journal-title":"J. Defense Manag."},{"issue":"03","key":"10.1016\/j.aei.2025.103988_b0035","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1142\/S2301385015500120","article-title":"Genetic fuzzy trees and their application towards autonomous training and control of a squadron of unmanned combat aerial vehicles","volume":"3","author":"Ernest","year":"2015","journal-title":"Unmanned Syst."},{"key":"10.1016\/j.aei.2025.103988_b0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111862","article-title":"Deep reinforcement learning\u2013based collision avoidance strategy for multiple unmanned aerial vehicles","volume":"160","author":"Kuo","year":"2025","journal-title":"Eng. Appl. Artif. Intel."},{"key":"10.1016\/j.aei.2025.103988_b0045","article-title":"Event-based deep reinforcement learning for quantum control","author":"Yu","year":"2023","journal-title":"IEEE Trans. Emerging Top. Comput. Intell."},{"issue":"2","key":"10.1016\/j.aei.2025.103988_b0050","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1109\/TETCI.2021.3066999","article-title":"An enhanced adaptivity of reinforcement learning-based temperature control in buildings using generalized training","volume":"6","author":"Taboga","year":"2021","journal-title":"IEEE Trans. Emerging Top. Comput. Intell."},{"key":"10.1016\/j.aei.2025.103988_b0055","article-title":"Physical-informed neural network in modeling and control of a servo mechanical rotor system","author":"Chen","year":"2025","journal-title":"Results Eng."},{"key":"10.1016\/j.aei.2025.103988_b0060","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.103180","article-title":"Reinforcement learning-based fuzzy controller for autonomous guided vehicle path tracking","volume":"65","author":"Kuo","year":"2025","journal-title":"Adv. Eng. Inf."},{"key":"10.1016\/j.aei.2025.103988_b0065","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2024.102965","article-title":"Artificial rabbits optimization\u2013based motion balance system for the impact recovery of a bipedal robot","volume":"63","author":"Kuo","year":"2025","journal-title":"Adv. Eng. Inf."},{"issue":"1","key":"10.1016\/j.aei.2025.103988_b0070","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1109\/TETCI.2018.2823329","article-title":"Starcraft micromanagement with reinforcement learning and curriculum transfer learning","volume":"3","author":"Shao","year":"2018","journal-title":"IEEE Trans. Emerging Top. Comput. Intell."},{"key":"10.1016\/j.aei.2025.103988_b0075","article-title":"Hierarchical coordination Multi-agent reinforcement learning with spatio-temporal abstraction","author":"Ma","year":"2023","journal-title":"IEEE Trans. Emerging Top. Comput. Intell."},{"key":"10.1016\/j.aei.2025.103988_b0080","doi-asserted-by":"crossref","DOI":"10.1109\/TETCI.2024.3372389","article-title":"Decentralized triggering and event-based integral reinforcement learning for multiplayer differential game systems","author":"Mu","year":"2024","journal-title":"IEEE Trans. Emerging Top. Comput. Intell."},{"key":"10.1016\/j.aei.2025.103988_b0085","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1109\/ACCESS.2019.2961426","article-title":"Maneuver decision of UAV in short-range air combat based on deep reinforcement learning","volume":"8","author":"Yang","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.aei.2025.103988_b0090","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint arXiv:1312.5602"},{"key":"10.1016\/j.aei.2025.103988_b0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.ast.2022.107857","article-title":"Autonomous decision-making for dogfights based on a tactical pursuit point approach","volume":"129","author":"Xu","year":"2022","journal-title":"Aerosp. Sci. Technol."},{"key":"10.1016\/j.aei.2025.103988_b0100","series-title":"International conference on machine learning","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"key":"10.1016\/j.aei.2025.103988_b0105","unstructured":"\u201cAlphaDogfight Trials Foreshadow Future of Human-Machine Symbiosis.\u201d https:\/\/www.darpa.mil\/news\/2020\/alphadogfight-trial (accessed 2025."},{"issue":"2","key":"10.1016\/j.aei.2025.103988_b0110","first-page":"154","article-title":"Alphadogfight trials: bringing autonomy to air combat","volume":"36","author":"DeMay","year":"2022","journal-title":"J. Hopkins APL Tech. Dig."},{"key":"10.1016\/j.aei.2025.103988_b0115","series-title":"2021 international conference on unmanned aircraft systems (ICUAS)","first-page":"275","article-title":"Hierarchical reinforcement learning for air-to-air combat","author":"Pope","year":"2021"},{"key":"10.1016\/j.aei.2025.103988_b0120","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018","journal-title":"arXiv preprint arXiv:1812.05905"},{"key":"10.1016\/j.aei.2025.103988_b0125","article-title":"Challenges of real-world reinforcement learning","author":"Dulac-Arnold","year":"2019","journal-title":"arXiv Preprint arXiv:1904.12901"},{"issue":"4\u20135","key":"10.1016\/j.aei.2025.103988_b0130","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1177\/0278364918770733","article-title":"The limits and potentials of deep learning for robotics","volume":"37","author":"S\u00fcnderhauf","year":"2018","journal-title":"Int. J. Robot. Res."},{"issue":"6","key":"10.1016\/j.aei.2025.103988_b0135","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1038\/s42254-021-00314-5","article-title":"Physics-informed machine learning","volume":"3","author":"Karniadakis","year":"2021","journal-title":"Nat. Rev. Phys."},{"key":"10.1016\/j.aei.2025.103988_b0140","series-title":"2023 IEEE 6th International Conference on Knowledge Innovation and Invention (ICKII)","first-page":"755","article-title":"Approximate Posture Increment Control for the Targeting Task of Differential Drive Robots","author":"Peng","year":"2023"},{"key":"10.1016\/j.aei.2025.103988_b0145","series-title":"International conference on machine learning","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"issue":"6","key":"10.1016\/j.aei.2025.103988_b0150","doi-asserted-by":"crossref","first-page":"1371","DOI":"10.1109\/TAI.2022.3222143","article-title":"Hierarchical reinforcement learning for air combat at DARPA's AlphaDogfight trials","volume":"4","author":"Pope","year":"2022","journal-title":"IEEE Trans. Artif. Intell."},{"key":"10.1016\/j.aei.2025.103988_b0155","unstructured":"J. S. Berndt, \u201cJSBSim,\u201d ed, 2011."},{"key":"10.1016\/j.aei.2025.103988_b0160","series-title":"Missile guidance and pursuit: kinematics, dynamics and control","author":"Shneydor","year":"1998"},{"key":"10.1016\/j.aei.2025.103988_b0165","doi-asserted-by":"crossref","unstructured":"Y. Bengio, J. Louradour, R. Collobert, and J. Weston, Curriculum learning, in Proceedings of the 26th annual international conference on machine learning, 2009, pp. 41\u201348.","DOI":"10.1145\/1553374.1553380"}],"container-title":["Advanced Engineering Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S147403462500881X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S147403462500881X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T06:29:17Z","timestamp":1773296957000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S147403462500881X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":33,"alternative-id":["S147403462500881X"],"URL":"https:\/\/doi.org\/10.1016\/j.aei.2025.103988","relation":{},"ISSN":["1474-0346"],"issn-type":[{"value":"1474-0346","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Physics-informed reinforcement learning for air-to-air F16 target aiming","name":"articletitle","label":"Article Title"},{"value":"Advanced Engineering Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.aei.2025.103988","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103988"}}