{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T08:02:10Z","timestamp":1773734530157,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62061002"],"award-info":[{"award-number":["62061002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2025.3533136","type":"journal-article","created":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T13:46:21Z","timestamp":1737639981000},"page":"38563-38579","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Proximal Policy Optimization for UAV Air Combat With Exploration Boosting and Covariance Matrix Adaptation Strategy"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8950-4274","authenticated-orcid":false,"given":"Zhuangfeng","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4686-7520","authenticated-orcid":false,"given":"Junzhe","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3507-4261","authenticated-orcid":false,"given":"Hongming","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenqin","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7452-0223","authenticated-orcid":false,"given":"Xueyun","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2514\/1.46815"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3053549"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.12.027"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0045-7825(99)00395-3"},{"issue":"11","key":"ref5","first-page":"1994","article-title":"An UAV air-combat decision expert system based on receding horizon control","volume":"41","author":"Li","year":"2015","journal-title":"J. Beijing Univ. Aeronautics Astronaut."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10620-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref11","article-title":"Dota 2 with large scale deep reinforcement learning","author":"OpenAI","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2024.102812"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ocecoaman.2024.107087"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610858"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2021.107382"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/iaeac47372.2019.8998066"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV50220.2020.9305467"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2961426"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-6463-0_24"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3060426"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.dt.2021.09.014"},{"key":"ref23","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA.2019.8899703"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVIDL51233.2020.000-7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3202918"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref28","first-page":"1861","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icimibd58123.2022.00022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-05058-6"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.20517\/ir.2023.04"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CoG51982.2022.9893690"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/DASC55683.2022.9925811"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3257849"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.23919\/CCC50068.2020.9188886"},{"key":"ref36","first-page":"2681","article-title":"Provably efficient maximum entropy exploration","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Hazan"},{"key":"ref37","first-page":"9443","article-title":"State entropy maximization with random encoders for efficient exploration","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Seo"},{"key":"ref38","article-title":"Limited-memory matrix adaptation for large scale black-box optimization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1705.06693"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP49062.2020.9231618"},{"key":"ref40","author":"Liu","year":"2022","journal-title":"Light Aircraft Game: A Lightweight, Scalable, Gym-wrapped Aircraft Competitive Environment With Baseline Reinforcement Learning Algorithms"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.2514\/6.2004-4923"},{"key":"ref42","first-page":"31811","article-title":"Accelerating reinforcement learning with value-conditional state entropy exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/10851300.pdf?arnumber=10851300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T05:44:03Z","timestamp":1773726243000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10851300\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3533136","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}