DC Field | Value | Language |
---|---|---|
dc.contributor.author | He, Shaoming | ko |
dc.contributor.author | Shin, Hyo-Sang | ko |
dc.contributor.author | Tsourdos, Antonios | ko |
dc.date.accessioned | 2024-03-18T10:00:49Z | - |
dc.date.available | 2024-03-18T10:00:49Z | - |
dc.date.created | 2024-03-18 | - |
dc.date.issued | 2021-08 | - |
dc.identifier.citation | JOURNAL OF AEROSPACE INFORMATION SYSTEMS, v.18, no.8, pp.571 - 582 | - |
dc.identifier.issn | 1940-3151 | - |
dc.identifier.uri | http://hdl.handle.net/10203/318572 | - |
dc.description.abstract | This paper aims to examine the potential of using the emerging deep reinforcement learning techniques in missile guidance applications. To this end, a Markovian decision process that enables the application of reinforcement learning theory to solve the guidance problem is formulated. A heuristic way is used to shape a proper reward function that has tradeoff between guidance accuracy, energy consumption, and interception time. The state-of-the-art deep deterministic policy gradient algorithm is used to learn an action policy that maps the observed engagements states to a guidance command. Extensive empirical numerical simulations are performed to validate the proposed computational guidance algorithm. | - |
dc.language | English | - |
dc.publisher | AMER INST AERONAUTICS ASTRONAUTICS | - |
dc.title | Computational Missile Guidance: A Deep Reinforcement Learning Approach | - |
dc.type | Article | - |
dc.identifier.wosid | 000683001600006 | - |
dc.identifier.scopusid | 2-s2.0-85114317291 | - |
dc.type.rims | ART | - |
dc.citation.volume | 18 | - |
dc.citation.issue | 8 | - |
dc.citation.beginningpage | 571 | - |
dc.citation.endingpage | 582 | - |
dc.citation.publicationname | JOURNAL OF AEROSPACE INFORMATION SYSTEMS | - |
dc.identifier.doi | 10.2514/1.I010970 | - |
dc.contributor.localauthor | Shin, Hyo-Sang | - |
dc.contributor.nonIdAuthor | He, Shaoming | - |
dc.contributor.nonIdAuthor | Tsourdos, Antonios | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordPlus | BIASED PNG LAW | - |
dc.subject.keywordPlus | IMPACT | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.