{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T13:56:18Z","timestamp":1780581378649,"version":"3.54.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106284"],"award-info":[{"award-number":["62106284"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007128","name":"Natural Science Foundation of Shaanxi Province, China","doi-asserted-by":"publisher","award":["2021JQ-370"],"award-info":[{"award-number":["2021JQ-370"]}],"id":[{"id":"10.13039\/501100007128","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Talent Fund of Association for Science and Technology in Shaanxi, China","award":["20220101"],"award-info":[{"award-number":["20220101"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3202938","type":"journal-article","created":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T21:08:51Z","timestamp":1661807331000},"page":"92177-92191","source":"Crossref","is-referenced-by-count":29,"title":["Unmanned Aerial Vehicle Swarm Cooperative Decision-Making for SEAD Mission: A Hierarchical Multiagent Reinforcement Learning Approach"],"prefix":"10.1109","volume":"10","author":[{"given":"Longfei","family":"Yue","sequence":"first","affiliation":[{"name":"Air Traffic Control and Navigation College, Air Force Engineering University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rennong","family":"Yang","sequence":"additional","affiliation":[{"name":"Air Traffic Control and Navigation College, Air Force Engineering University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialiang","family":"Zuo","sequence":"additional","affiliation":[{"name":"Air Traffic Control and Navigation College, Air Force Engineering University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Air Traffic Control and Navigation College, Air Force Engineering University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiuni","family":"Li","sequence":"additional","affiliation":[{"name":"Aeronautics Engineering College, Air Force Engineering University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xi’an Modern Control Technology Research Institute, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2514\/6.1999-4185"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/nav.10046"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2514\/6.2006-6456"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2514\/1.53860"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5139\/JKSAS.2020.48.11.935"},{"issue":"4","key":"ref6","first-page":"10","article-title":"Research on intelligent cooperative combat system in air defense suppression mission","volume":"3","author":"Wang","year":"2020","journal-title":"Unmanned Syst. Technol."},{"key":"ref7","article-title":"An adaptive maneuvering logic computer program for the simulation of one-on-one air-to-air combat","author":"Burgin","year":"1975"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2514\/6.1989-3312"},{"key":"ref9","first-page":"859","article-title":"An influence diagram approach to one-on-one air combat","volume-title":"Proc. 10th Int. Symp. Differ. Games Appl.","volume":"2","author":"Virtanen"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2514\/1.17168"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.4172\/2167-0374.1000144"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/9843735"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2020.05.011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2020.12.027"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2985576"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS51884.2021.9476700"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.104112"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-27535-8_48"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref20","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"issue":"4","key":"ref21","doi-asserted-by":"crossref","first-page":"1038","DOI":"10.1016\/j.cja.2013.04.040","article-title":"Real-time trajectory planning for UCAV air-to-surface attack using inverse dynamics optimization method and receding horizon control","volume":"26","author":"Yu","year":"2013","journal-title":"Chin. J. Aeronaut."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.7249\/RR4311"},{"key":"ref23","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref26","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref27","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2993459"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"issue":"1","key":"ref30","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1022140919877","article-title":"Recent advances in hierarchical reinforcement learning","volume":"13","author":"Barto","year":"2003","journal-title":"Discrete Event Dyn. Syst."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2012.05.008"},{"key":"ref32","first-page":"709","article-title":"Optimal policy switching algorithms for reinforcement learning","volume-title":"Proc. 9th Int. Conf. Auto. Agents Multiagent Syst. (AAMAS)","author":"Comanici"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref34","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Vezhnevets"},{"key":"ref35","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nachum"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1117\/12.2585808"},{"key":"ref37","article-title":"Multiagent cooperation and competition with deep reinforcement learning","author":"Tampuu","year":"2015","journal-title":"arXiv:1511.08779"},{"key":"ref38","article-title":"Is independent learning all you need in the StarCraft multi-agent challenge?","author":"de Witt","year":"2020","journal-title":"arXiv:2011.09533"},{"key":"ref39","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"Rashid","year":"2018","journal-title":"arXiv:1803.11485"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3020067"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09869884.pdf?arnumber=9869884","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T06:07:51Z","timestamp":1709359671000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9869884\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3202938","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}