{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T20:08:09Z","timestamp":1784923689371,"version":"3.55.0"},"reference-count":23,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"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":["U2233209"],"award-info":[{"award-number":["U2233209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Basic Research Program of Shaanxi","award":["2024JC-YBQN-0668"],"award-info":[{"award-number":["2024JC-YBQN-0668"]}]},{"name":"Shaanxi Key Project","award":["2025JC-QYCX-052"],"award-info":[{"award-number":["2025JC-QYCX-052"]}]},{"name":"Project for Science and Technology","award":["2022-JCJQ-QT-018"],"award-info":[{"award-number":["2022-JCJQ-QT-018"]}]},{"name":"Young Talent Fund of Association for Science and Technology in Shaanxi","award":["20220101"],"award-info":[{"award-number":["20220101"]}]},{"name":"Postdoctoral International Exchange Project","award":["YJ20220347"],"award-info":[{"award-number":["YJ20220347"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62303489"],"award-info":[{"award-number":["62303489"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["GKJJ24050502"],"award-info":[{"award-number":["GKJJ24050502"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postdoctoral Science Foundation General Program","award":["2022M723877"],"award-info":[{"award-number":["2022M723877"]}]},{"name":"Postdoctoral Science Foundation Special Funding","award":["2023T160790"],"award-info":[{"award-number":["2023T160790"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/lra.2025.3641098","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:42:20Z","timestamp":1765219340000},"page":"1138-1145","source":"Crossref","is-referenced-by-count":5,"title":["Supervision-Enhanced Deep Reinforcement Learning for Hybrid Action in BVR Engagement"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0728-3993","authenticated-orcid":false,"given":"Haoran","family":"Han","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6966-0531","authenticated-orcid":false,"given":"Jian","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6406-2399","authenticated-orcid":false,"given":"Maolong","family":"Lv","sequence":"additional","affiliation":[{"name":"Air Traffic Control and Navigation College, Air Force Engineering University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6467-896X","authenticated-orcid":false,"given":"Li","family":"Mo","sequence":"additional","affiliation":[{"name":"School of Aerospace Engineering, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3285223"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2025.3568377"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3222143"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2025.3578294"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3391691"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119285"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.104112"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.dt.2023.08.019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2025.3579745"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2024.04.008"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2024.3410249"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2024.109285"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/taes.2025.3571405"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2025.3582119"},{"key":"ref15","article-title":"Soft actor-critic for discrete action settings","author":"Christodoulou","year":"2019"},{"key":"ref16","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Haarnoja","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3576178"},{"key":"ref19","volume-title":"Aircraft Control and Simulation","author":"Stevens","year":"2003"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/app13148283"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SMC54092.2024.10831270"},{"key":"ref22","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CSPA64953.2025.10933185"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11293803\/11282447.pdf?arnumber=11282447","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T10:59:40Z","timestamp":1766055580000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11282447\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":23,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3641098","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}