Performance improvement of evolution strategies using reinforcement learning
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Sang-Hwan | - |
dc.contributor.author | Jun, Hyo-Byung | - |
dc.contributor.author | Sim, Kwee-Bo | - |
dc.date.accessioned | 2022-04-14T09:40:34Z | - |
dc.date.available | 2022-04-14T09:40:34Z | - |
dc.date.issued | 1999-08 | - |
dc.identifier.issn | 0000-0000 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/56566 | - |
dc.description.abstract | In this paper, we propose a new type of evolution strategies combined with reinforcement learning. We use the change of fitness occurred by mutation to make the reinforcement signals which estimate and control the step length of mutation. With this proposed method, the convergence rate is improved. Also, we use Cauchy distributed mutation to increase global convergence faculty. Cauchy distributed mutation is more likely to escape from a local minimum or move away from a plateau than Gaussian distributed mutation. After an outline of the history of evolution strategies, we will explain the evolution strategies combined with the reinforcement learning, that is reinforcement evolution strategies. The performance of proposed method will be estimated by comparison with conventional evolution strategies on several test problems. | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | IEEE, Piscataway, NJ, United States | - |
dc.title | Performance improvement of evolution strategies using reinforcement learning | - |
dc.type | Article | - |
dc.identifier.bibliographicCitation | IEEE International Conference on Fuzzy Systems, v.2, pp II - 639 - II-644 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.scopusid | 2-s2.0-0033280093 | - |
dc.citation.endPage | 639 - II-644 | - |
dc.citation.startPage | II | - |
dc.citation.title | IEEE International Conference on Fuzzy Systems | - |
dc.citation.volume | 2 | - |
dc.type.docType | Conference Paper | - |
dc.subject.keywordPlus | Convergence of numerical methods | - |
dc.subject.keywordPlus | Estimation | - |
dc.subject.keywordPlus | Learning systems | - |
dc.subject.keywordPlus | Mathematical operators | - |
dc.subject.keywordPlus | Performance | - |
dc.subject.keywordPlus | Probability density function | - |
dc.subject.keywordPlus | Probability distributions | - |
dc.subject.keywordPlus | Vectors | - |
dc.subject.keywordPlus | Cauchy distributed mutation | - |
dc.subject.keywordPlus | Evolution strategies | - |
dc.subject.keywordPlus | Gaussian distributed mutation | - |
dc.subject.keywordPlus | Reinforcement learning | - |
dc.subject.keywordPlus | Genetic algorithms | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.