{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:21:00Z","timestamp":1773771660951,"version":"3.50.1"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012492","name":"Youth Innovation Promotion Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012492","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/cog51982.2022.9893690","type":"proceedings-article","created":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T19:33:31Z","timestamp":1663702411000},"page":"616-619","source":"Crossref","is-referenced-by-count":15,"title":["Learning Continuous 3-DoF Air-to-Air Close-in Combat Strategy using Proximal Policy Optimization"],"prefix":"10.1109","author":[{"given":"Luntong","family":"Li","sequence":"first","affiliation":[{"name":"Institute of AutomationChinese Academy of Sciences,The State Key Laboratory of Management and Control for Complex Systems,Beijing,China,100190"}]},{"given":"Zhiming","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute of Automation Chinese Academy of Sciences,Integrated Information System Research Center,Beijing,China,100190"}]},{"given":"Jiajun","family":"Chai","sequence":"additional","affiliation":[{"name":"Institute of AutomationChinese Academy of Sciences,The State Key Laboratory of Management and Control for Complex Systems,Beijing,China,100190"}]},{"given":"Zhen","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation Chinese Academy of Sciences,Integrated Information System Research Center,Beijing,China,100190"}]},{"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of AutomationChinese Academy of Sciences,The State Key Laboratory of Management and Control for Complex Systems,Beijing,China,100190"}]},{"given":"Jianqiang","family":"Yi","sequence":"additional","affiliation":[{"name":"Institute of Automation Chinese Academy of Sciences,Integrated Information System Research Center,Beijing,China,100190"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2514\/1.46815"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.4172\/2167-0374.1000144"},{"key":"ref12","first-page":"1318","article-title":"Integrated hybrid planning and programmed control for real time UAV maneuvering","author":"ramirez","year":"2018","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref13","article-title":"Proximal policy optimization algorithms","volume":"20","author":"schulman","year":"0","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CAC48633.2019.8996232"},{"key":"ref15","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref4","article-title":"BNAS: Efficient neural architecture search using broad scalable architecture","author":"ding","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref3","article-title":"Missile guidance with assisted deep reinforcement learning for head-on interception of maneuvering target","author":"li","year":"2021","journal-title":"Complex Intell Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS51884.2021.9476700"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004395"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2020.3022698"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041469"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICICIP53388.2021.9642160"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.104112"},{"key":"ref1","first-page":"48","article-title":"Nightfall: Machine autonomy in air-to-air combat","volume":"28","author":"byrnes","year":"2014","journal-title":"Air Space Power J"}],"event":{"name":"2022 IEEE Conference on Games (CoG)","location":"Beijing, China","start":{"date-parts":[[2022,8,21]]},"end":{"date-parts":[[2022,8,24]]}},"container-title":["2022 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9893561\/9893544\/09893690.pdf?arnumber=9893690","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T20:25:29Z","timestamp":1665433529000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9893690\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/cog51982.2022.9893690","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}