A survey of deep reinforcement learning technologies for intelligent air combat

Major aviation nations and related research institutions are focusing on exploration and research of key technologies for intelligent air combat. Deep reinforcement learning combines the perceptual ability of deep learning with the decision-making ability of reinforcement learning, demonstrating sig...

Full description

Saved in:
Bibliographic Details
Main Authors: LI Ni, LIAN Yunxiao, ZHOU Pan, XIE Feng, TANG Zhili, ZHOU Haoran, CHEN Jun
Format: Article
Language:zho
Published: Editorial Department of Advances in Aeronautical Science and Engineering 2025-06-01
Series:Hangkong gongcheng jinzhan
Subjects:
Online Access:http://hkgcjz.cnjournals.com/hkgcjz/article/abstract/2024049
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849469581516603392
author LI Ni
LIAN Yunxiao
ZHOU Pan
XIE Feng
TANG Zhili
ZHOU Haoran
CHEN Jun
author_facet LI Ni
LIAN Yunxiao
ZHOU Pan
XIE Feng
TANG Zhili
ZHOU Haoran
CHEN Jun
author_sort LI Ni
collection DOAJ
description Major aviation nations and related research institutions are focusing on exploration and research of key technologies for intelligent air combat. Deep reinforcement learning combines the perceptual ability of deep learning with the decision-making ability of reinforcement learning, demonstrating significant advantages in the emergence of air combat capabilities. Based on the urgent needs of intelligent air combat development, the points of integration with the air combat field are explored by analyzing and summarizing the mainstream algorithms in the field of deep reinforcement learning. From the perspective of algorithm implementation, the key technologies of deep reinforcement learning in air combat are pointed out. By sorting out the current cutting-edge technological achievements in the field of air combat, it is concluded that the future research on deep reinforcement learning will develop from single-to-single air combat to cluster air combat. The challenges algorithm faced are proposed, which can provide the reference and guidance for the development of intelligent algorithms in intelligent air combat.
format Article
id doaj-art-8fc68d25ba714cb2bfd7c14c354e40ba
institution Kabale University
issn 1674-8190
language zho
publishDate 2025-06-01
publisher Editorial Department of Advances in Aeronautical Science and Engineering
record_format Article
series Hangkong gongcheng jinzhan
spelling doaj-art-8fc68d25ba714cb2bfd7c14c354e40ba2025-08-20T03:25:26ZzhoEditorial Department of Advances in Aeronautical Science and EngineeringHangkong gongcheng jinzhan1674-81902025-06-0116311610.16615/j.cnki.1674-8190.2025.03.01hkgcjz-16-3-1A survey of deep reinforcement learning technologies for intelligent air combatLI Ni0LIAN Yunxiao1ZHOU Pan2XIE Feng3TANG Zhili4ZHOU Haoran5CHEN Jun6School of Aeronautics, Northwestern Polytechnical University, Xi'an 710072, ChinaSchool of Aeronautics, Northwestern Polytechnical University, Xi'an 710072, ChinaSchool of Aeronautics, Northwestern Polytechnical University, Xi'an 710072, ChinaAVIC Chengdu Aircraft Design and Research Institute, Chengdu 610041, ChinaSchool of Aeronautics, Northwestern Polytechnical University, Xi'an 710072, ChinaSchool of Cybersecurity, Northwestern Polytechnical University, Xi'an 710129, ChinaSchool of Electronics and Information, Northwestern Polytechnical University, Xi'an 710129, ChinaMajor aviation nations and related research institutions are focusing on exploration and research of key technologies for intelligent air combat. Deep reinforcement learning combines the perceptual ability of deep learning with the decision-making ability of reinforcement learning, demonstrating significant advantages in the emergence of air combat capabilities. Based on the urgent needs of intelligent air combat development, the points of integration with the air combat field are explored by analyzing and summarizing the mainstream algorithms in the field of deep reinforcement learning. From the perspective of algorithm implementation, the key technologies of deep reinforcement learning in air combat are pointed out. By sorting out the current cutting-edge technological achievements in the field of air combat, it is concluded that the future research on deep reinforcement learning will develop from single-to-single air combat to cluster air combat. The challenges algorithm faced are proposed, which can provide the reference and guidance for the development of intelligent algorithms in intelligent air combat.http://hkgcjz.cnjournals.com/hkgcjz/article/abstract/2024049intelligent air combatdeep reinforcement learningcombat aircraftkey technologiesdevelopment trend
spellingShingle LI Ni
LIAN Yunxiao
ZHOU Pan
XIE Feng
TANG Zhili
ZHOU Haoran
CHEN Jun
A survey of deep reinforcement learning technologies for intelligent air combat
Hangkong gongcheng jinzhan
intelligent air combat
deep reinforcement learning
combat aircraft
key technologies
development trend
title A survey of deep reinforcement learning technologies for intelligent air combat
title_full A survey of deep reinforcement learning technologies for intelligent air combat
title_fullStr A survey of deep reinforcement learning technologies for intelligent air combat
title_full_unstemmed A survey of deep reinforcement learning technologies for intelligent air combat
title_short A survey of deep reinforcement learning technologies for intelligent air combat
title_sort survey of deep reinforcement learning technologies for intelligent air combat
topic intelligent air combat
deep reinforcement learning
combat aircraft
key technologies
development trend
url http://hkgcjz.cnjournals.com/hkgcjz/article/abstract/2024049
work_keys_str_mv AT lini asurveyofdeepreinforcementlearningtechnologiesforintelligentaircombat
AT lianyunxiao asurveyofdeepreinforcementlearningtechnologiesforintelligentaircombat
AT zhoupan asurveyofdeepreinforcementlearningtechnologiesforintelligentaircombat
AT xiefeng asurveyofdeepreinforcementlearningtechnologiesforintelligentaircombat
AT tangzhili asurveyofdeepreinforcementlearningtechnologiesforintelligentaircombat
AT zhouhaoran asurveyofdeepreinforcementlearningtechnologiesforintelligentaircombat
AT chenjun asurveyofdeepreinforcementlearningtechnologiesforintelligentaircombat
AT lini surveyofdeepreinforcementlearningtechnologiesforintelligentaircombat
AT lianyunxiao surveyofdeepreinforcementlearningtechnologiesforintelligentaircombat
AT zhoupan surveyofdeepreinforcementlearningtechnologiesforintelligentaircombat
AT xiefeng surveyofdeepreinforcementlearningtechnologiesforintelligentaircombat
AT tangzhili surveyofdeepreinforcementlearningtechnologiesforintelligentaircombat
AT zhouhaoran surveyofdeepreinforcementlearningtechnologiesforintelligentaircombat
AT chenjun surveyofdeepreinforcementlearningtechnologiesforintelligentaircombat