{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:25:16Z","timestamp":1772119516152,"version":"3.50.1"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Municipal Natural Science Foundation","doi-asserted-by":"publisher","award":["Z220004"],"award-info":[{"award-number":["Z220004"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Municipal Natural Science Foundation","doi-asserted-by":"publisher","award":["L202012"],"award-info":[{"award-number":["L202012"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2023ZCJH02"],"award-info":[{"award-number":["2023ZCJH02"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3383322","type":"journal-article","created":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T18:23:20Z","timestamp":1711736600000},"page":"48210-48222","source":"Crossref","is-referenced-by-count":5,"title":["Guidance Design for Escape Flight Vehicle Using Evolution Strategy Enhanced Deep Reinforcement Learning"],"prefix":"10.1109","volume":"12","author":[{"given":"Xiao","family":"Hu","sequence":"first","affiliation":[{"name":"School of Aerospace Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianshu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Aerospace Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3011-7858","authenticated-orcid":false,"given":"Min","family":"Gong","sequence":"additional","affiliation":[{"name":"China Academy of Launch Vehicle Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2395-1637","authenticated-orcid":false,"given":"Shaoshi","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"9","key":"ref1","first-page":"1583","article-title":"Guidance based on zero effort miss for super-range exoatmospheric intercept","volume":"30","author":"Chen","year":"2009","journal-title":"Acta Aeronautica et Astronautica Sinica"},{"issue":"7","key":"ref2","first-page":"1768","article-title":"A zero-effort miss distance-based guidance law for endoatmoshperic interceptor","volume":"31","author":"Liu","year":"2010","journal-title":"J. Astronaut."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2006.04.037"},{"issue":"6","key":"ref4","first-page":"11","article-title":"A linear quadratic optimal guidance method for lunar soft landing","volume":"24","author":"Huang","year":"2006","journal-title":"Aerosp. Control"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2828088"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2019.12.009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2022.107651"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2021.106776"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2018.10.013"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2514\/1.G004446"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CGNCC.2016.7828936"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2514\/1.50923"},{"key":"ref13","author":"Goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref14","author":"Sutton","year":"2019","journal-title":"Reinforcement Learning"},{"key":"ref15","article-title":"Trust region policy optimization","author":"Schulman","year":"2015","journal-title":"arXiv:1502.05477"},{"key":"ref16","article-title":"Truly proximal policy optimization","author":"Wang","year":"2019","journal-title":"arXiv:1903.07940"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1023\/A:1015059928466"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3029475"},{"issue":"2","key":"ref22","first-page":"414","article-title":"Q-learning reinforcement learning guidance law","volume":"42","author":"Zhang","year":"2020","journal-title":"Syst. Eng. Electron."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2909579"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5430\/air.v4n1p60"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2020.105746"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3022600"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICUS50048.2020.9274975"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2018.09.004"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2020.3015321"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2022.3178770"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3170458"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3016024"},{"key":"ref33","author":"Qian","year":"2014","journal-title":"Missile Flight Aerodynamics"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref35","article-title":"Guidance design for the interception of hypersonic boost glide vehicles","author":"Fu","year":"2019"},{"key":"ref36","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10485410.pdf?arnumber=10485410","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T21:10:59Z","timestamp":1712610659000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10485410\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3383322","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}