{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:51:48Z","timestamp":1775667108142,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61802428"],"award-info":[{"award-number":["61802428"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2019M651991"],"award-info":[{"award-number":["2019M651991"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Defense of Science and Technology"},{"name":"Science and Technology Commission of the Military Commission","award":["2019-JCJQ-JJ-014"],"award-info":[{"award-number":["2019-JCJQ-JJ-014"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Rel."],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/tr.2022.3158279","type":"journal-article","created":{"date-parts":[[2022,3,28]],"date-time":"2022-03-28T20:44:59Z","timestamp":1648500299000},"page":"763-774","source":"Crossref","is-referenced-by-count":23,"title":["Improving Autonomous Behavior Strategy Learning in an Unmanned Swarm System Through Knowledge Enhancement"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-2325","authenticated-orcid":false,"given":"Tingting","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Command and Control Engineering, Army Engineering University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lai","family":"Chai","sequence":"additional","affiliation":[{"name":"School of Command and Control Engineering, Army Engineering University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0203-934X","authenticated-orcid":false,"given":"Shenshen","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junyu","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Command and Control Engineering, Army Engineering University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8342-4623","authenticated-orcid":false,"given":"Xiaofan","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1982-6780","authenticated-orcid":false,"given":"Aiguo","family":"Song","sequence":"additional","affiliation":[{"name":"School of Instrumental Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yushi","family":"Lan","sequence":"additional","affiliation":[{"name":"28th Research Institute of China Electronics Technology Group Corporation, National Defense, Science, and Technology Key Laboratory, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2967061"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.05.062"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1504\/IJAAC.2020.110075"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23940\/ijpe.21.09.p2.756-765"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2880468"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2946153"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2017.2678480"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2017.2761827"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2018.2880467"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2951770"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23940\/ijpe.20.04.p14.629638"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3084238"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2840143"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2926279"},{"issue":"6","key":"ref15","first-page":"26","article-title":"A brief survey of deep reinforcement learning","volume":"34","author":"Arulkumaran","year":"2017","journal-title":"Inst. Electr. Electron. Eng."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23940\/ijpe.21.07.p2.579588"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9091363"},{"key":"ref19","first-page":"15931","article-title":"Learning to utilize shaping rewards: A new approach of reward shaping","volume-title":"Proc. 34th Conf. Neur. Inf. Process. Syst.","author":"Hu","year":"2020"},{"key":"ref20","first-page":"757","article-title":"Multi-UAV cooperative autonomous navigation based on multi-agent deep deterministic policy gradient","volume":"42","author":"Li","year":"2021","journal-title":"J. Astronaut."},{"key":"ref21","article-title":"Parametrized deep Q-networks learning: Reinforcement learning with discrete continuous hybrid action space","author":"Xiong","year":"2018"},{"key":"ref22","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lillicrap","year":"2016"},{"key":"ref23","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017","journal-title":"Adv. Neu. Inf. Process. Syst."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3036416"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2020.107056"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2976121"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.2973376"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.3024610"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2020.3032744"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2021.3062045"},{"issue":"12","key":"ref32","first-page":"3656","article-title":"Research on collaborative strategy based on GAED-MADDPG multi-agent reinforcement learning","volume":"37","author":"Zou","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3016951"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3016951"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVIDL51233.2020.000-7"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3011670"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/AICI.2009.147"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s12518-013-0120-x"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1177\/0305829820971694"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3103\/S1068798X20070187"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAR.2016.7486728"},{"key":"ref42","first-page":"3","volume-title":"Reinforcement Learning and Markov Decision Processes, Reinforcement Learning","author":"Otterlo","year":"2012"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.014"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"}],"container-title":["IEEE Transactions on Reliability"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/24\/9787285\/09743553.pdf?arnumber=9743553","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T00:49:39Z","timestamp":1705538979000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9743553\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":44,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tr.2022.3158279","relation":{},"ISSN":["0018-9529","1558-1721"],"issn-type":[{"value":"0018-9529","type":"print"},{"value":"1558-1721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6]]}}}