{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T15:55:05Z","timestamp":1778255705142,"version":"3.51.4"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3257849","type":"journal-article","created":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T17:53:19Z","timestamp":1678989199000},"page":"26427-26440","source":"Crossref","is-referenced-by-count":40,"title":["Deep Reinforcement Learning-Based Air-to-Air Combat Maneuver Generation in a Realistic Environment"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1031-2694","authenticated-orcid":false,"given":"Jung Ho","family":"Bae","sequence":"first","affiliation":[{"name":"Agency for Defense Development, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0693-810X","authenticated-orcid":false,"given":"Hoseong","family":"Jung","sequence":"additional","affiliation":[{"name":"Agency for Defense Development, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seogbong","family":"Kim","sequence":"additional","affiliation":[{"name":"Agency for Defense Development, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungho","family":"Kim","sequence":"additional","affiliation":[{"name":"Agency for Defense Development, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong-Duk","family":"Kim","sequence":"additional","affiliation":[{"name":"Agency for Defense Development, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CAC.2018.8623434"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00138"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1142\/S2301385015500120"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref6","volume-title":"Heron Systems at DARPA Alpha Dogfight Trials","author":"Inc","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV50220.2020.9305467"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IAEAC47372.2019.8998066"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2961426"},{"key":"ref10","article-title":"Reinforcement learning based air combat maneuver generation","author":"Ozbek","year":"2022","journal-title":"arXiv:2201.05528"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3202918"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3060426"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9071121"},{"key":"ref14","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref17","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref18","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Fujimoto"},{"key":"ref19","article-title":"If MaxEnt RL is the answer, what is the question?","author":"Eysenbach","year":"2019","journal-title":"arXiv:1910.01913"},{"key":"ref20","first-page":"1","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(65)90154-X"},{"key":"ref22","first-page":"1","article-title":"Deep recurrent Q-learning for partially observable MDPs","volume-title":"Proc. Assoc. Adv. Artif. Intell. (AAAI) Fall Symp. Ser.","author":"Hausknecht"},{"key":"ref23","article-title":"Mask Atari for deep reinforcement learning as POMDP benchmarks","author":"Shao","year":"2022","journal-title":"arXiv:2203.16777"},{"key":"ref24","article-title":"Deep recurrent Q-learning vs deep Q-learning on a simple partially observable Markov decision process with minecraft","author":"Romac","year":"2019","journal-title":"arXiv:1903.04311"},{"key":"ref25","article-title":"Memory-based control with recurrent neural networks","author":"Heess","year":"2015","journal-title":"arXiv:1512.04455"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636140"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref29","first-page":"1","article-title":"Recurrent off-policy baselines for memory-based continuous control","volume-title":"Proc. Deep RL Workshop, Neural Inf. Process. Syst. (NeurIPS)","author":"Yang"},{"key":"ref30","first-page":"1","article-title":"Recurrent experience replay in distributed reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kapturowski"},{"key":"ref31","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","first-page":"1","article-title":"How crucial is transformer in decision transformer?","volume-title":"Proc. Neural Inf. Process. Syst. (NeurIPS) Found. Modeling Decis. Making Workshop","author":"Siebenborn"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS51884.2021.9476700"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.2514\/6.2004-4923"},{"key":"ref36","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref38","first-page":"1753","article-title":"Air-to-air BFM engagement simulator for AI engagement model","volume-title":"Proc. Korea Inst. Mil. Sci. Technol. Conf.","author":"Oh"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.9766\/KIMST.2022.25.6.637"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10072404.pdf?arnumber=10072404","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T13:37:57Z","timestamp":1707831477000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10072404\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3257849","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}