{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T19:39:49Z","timestamp":1783021189125,"version":"3.54.6"},"reference-count":26,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100010097","name":"China Association for Science and Technology","doi-asserted-by":"publisher","award":["2024-JCJQ-QT-034"],"award-info":[{"award-number":["2024-JCJQ-QT-034"]}],"id":[{"id":"10.13039\/100010097","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306329"],"award-info":[{"award-number":["62306329"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Hunan Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2024JJ6478"],"award-info":[{"award-number":["2024JJ6478"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Hunan Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2023JJ40676"],"award-info":[{"award-number":["2023JJ40676"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.engappai.2026.115305","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T12:19:44Z","timestamp":1781266784000},"page":"115305","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P1","title":["Trajectory-level reward relabelling and progressive sub-task flight control for engineering-grade simulation of adversarial aerial engagements"],"prefix":"10.1016","volume":"181","author":[{"given":"Hesong","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinmeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanjun","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.115305_b1","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","first-page":"13544","article-title":"RUDDER: Return decomposition for delayed rewards","volume":"vol. 32","author":"Arjona-Medina","year":"2019"},{"issue":"9","key":"10.1016\/j.engappai.2026.115305_b2","doi-asserted-by":"crossref","first-page":"5417","DOI":"10.1109\/TSMC.2023.3270444","article-title":"A hierarchical deep reinforcement learning framework for 6-DOF ucav air-to-air combat","volume":"53","author":"Chai","year":"2023","journal-title":"IEEE Trans. Syst. Man, Cybern.: Syst."},{"key":"10.1016\/j.engappai.2026.115305_b3","series-title":"Randomized ensembled double q-learning: Learning fast without a model","author":"Chen","year":"2021"},{"key":"10.1016\/j.engappai.2026.115305_b4","series-title":"Advances in Neural Information Processing Systems","first-page":"13550","article-title":"Heuristic-guided reinforcement learning","volume":"vol. 34","author":"Cheng","year":"2021"},{"issue":"18","key":"10.1016\/j.engappai.2026.115305_b5","doi-asserted-by":"crossref","first-page":"17037","DOI":"10.1007\/s11071-023-08725-y","article-title":"A deep reinforcement learning control approach for high-performance aircraft","volume":"111","author":"De Marco","year":"2023","journal-title":"Nonlinear Dynam."},{"issue":"5","key":"10.1016\/j.engappai.2026.115305_b6","doi-asserted-by":"crossref","first-page":"3935","DOI":"10.1109\/TPAMI.2025.3537087","article-title":"Distributional soft actor-critic with three refinements","volume":"47","author":"Duan","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.115305_b7","unstructured":"Gangwani, T., Zhou, Y., Peng, J., 2020. Learning Guidance Rewards with Trajectory-space Smoothing. In: Advances in Neural Information Processing Systems (NeurIPS)."},{"issue":"5","key":"10.1016\/j.engappai.2026.115305_b8","doi-asserted-by":"crossref","first-page":"12892","DOI":"10.1109\/TAES.2025.3578294","article-title":"Augmenting the robustness of tactical maneuver decision-making in unmanned aerial combat vehicles during dogfights via prioritized population play with diversified partners","volume":"61","author":"Han","year":"2025","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"issue":"2","key":"10.1016\/j.engappai.2026.115305_b9","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.1109\/LRA.2025.3641098","article-title":"Supervision-enhanced deep reinforcement learning for hybrid action in BVR engagement","volume":"11","author":"Han","year":"2026","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.engappai.2026.115305_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2022.104767","article-title":"Aerial combat maneuvering policy learning based on confrontation demonstrations and dynamic quality replay","volume":"111","author":"Hu","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115305_b11","first-page":"97","article-title":"Intelligent maneuvering decision of unmanned combat aircraft based on LSTM-dueling DQN","volume":"6","author":"Hu","year":"2021","journal-title":"Tactical Missile Technol"},{"key":"10.1016\/j.engappai.2026.115305_b12","series-title":"International Conference on Machine Learning","first-page":"5556","article-title":"Controlling overestimation bias with truncated mixture of continuous distributional quantile critics","author":"Kuznetsov","year":"2020"},{"key":"10.1016\/j.engappai.2026.115305_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.113015","article-title":"A curriculum-guided and explainable reinforcement learning framework for fixed-wing unmanned aerial vehicle autopilots","volume":"163","author":"Lian","year":"2026","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115305_b14","series-title":"2021 International Conference on Unmanned Aircraft Systems","first-page":"275","article-title":"Hierarchical reinforcement learning for air-to-air combat","author":"Pope","year":"2021"},{"key":"10.1016\/j.engappai.2026.115305_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.123084","article-title":"H3E: Learning air combat with a three-level hierarchical framework embedding expert knowledge","volume":"245","author":"Qian","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.engappai.2026.115305_b16","unstructured":"Reddy, S., Dragan, A.D., Levine, S., 2020. SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards. In: 8th International Conference on Learning Representations (ICLR 2020)."},{"key":"10.1016\/j.engappai.2026.115305_b17","first-page":"47","article-title":"Continuous decision-making method for autonomous air combat","volume":"13","author":"Shan","year":"2022","journal-title":"Adv. Aeronaut. Sci. Eng"},{"issue":"1","key":"10.1016\/j.engappai.2026.115305_b18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10462-023-10620-2","article-title":"Deep reinforcement learning-based air combat maneuver decision-making: literature review, implementation tutorial and future direction","volume":"57","author":"Wang","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.engappai.2026.115305_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109460","article-title":"Intelligent recognition method of target tactical behavior intention in air combat based on deep learning","volume":"138","author":"Wang","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115305_b20","series-title":"2019 IEEE 4th Advanced Information Technology, Electronic and Automation Control Conference","first-page":"538","article-title":"Autonomous decision-making method for combat mission of UAV based on deep reinforcement learning","volume":"vol. 1","author":"Xu","year":"2019"},{"key":"10.1016\/j.engappai.2026.115305_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.126069","article-title":"Multi-UAV air combat cooperative game based on virtual opponent and value attention decomposition policy gradient","volume":"267","author":"Xu","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.engappai.2026.115305_b22","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.engappai.2026.115305_b23","series-title":"2022 IEEE\/AIAA 41st Digital Avionics Systems Conference","first-page":"1","article-title":"Deep reinforcement learning-based intelligent agent for autonomous air combat","author":"Yoo","year":"2022"},{"issue":"5","key":"10.1016\/j.engappai.2026.115305_b24","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1016\/j.cja.2024.03.009","article-title":"Loyal wingman task execution for future aerial combat: A hierarchical prior-based reinforcement learning approach","volume":"37","author":"ZHANG","year":"2024","journal-title":"Chin. J. Aeronaut."},{"issue":"4","key":"10.1016\/j.engappai.2026.115305_b25","article-title":"Intelligent air combat decision making and simulation based on deep reinforcement learning","volume":"44","author":"Zhou","year":"2023","journal-title":"Acta Aeronaut. et Astronaut. Sin."},{"key":"10.1016\/j.engappai.2026.115305_b26","doi-asserted-by":"crossref","first-page":"8129","DOI":"10.1109\/ACCESS.2020.2964031","article-title":"Learning system for air combat decision inspired by cognitive mechanisms of the brain","volume":"8","author":"Zhou","year":"2020","journal-title":"IEEE Access"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626015897?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626015897?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T18:44:03Z","timestamp":1783017843000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626015897"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":26,"alternative-id":["S0952197626015897"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115305","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Trajectory-level reward relabelling and progressive sub-task flight control for engineering-grade simulation of adversarial aerial engagements","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115305","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115305"}}