Performance improvement of evolution strategies using reinforcement learning

K. Sim, Ho-Byung Chun
{"title":"Performance improvement of evolution strategies using reinforcement learning","authors":"K. Sim, Ho-Byung Chun","doi":"10.1109/FUZZY.1999.793017","DOIUrl":null,"url":null,"abstract":"We propose a new type of evolution strategies combined with reinforcement learning. We use the change of fitness occurred by mutation to form 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 the 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 explain the evolution strategies combined with the reinforcement learning, that is reinforcement evolution strategies. Performance of the proposed method is estimated by comparison with conventional evolution strategies on several test problems.","PeriodicalId":344788,"journal":{"name":"FUZZ-IEEE'99. 1999 IEEE International Fuzzy Systems. Conference Proceedings (Cat. No.99CH36315)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2001-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"FUZZ-IEEE'99. 1999 IEEE International Fuzzy Systems. Conference Proceedings (Cat. No.99CH36315)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/FUZZY.1999.793017","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 11

Abstract

We propose a new type of evolution strategies combined with reinforcement learning. We use the change of fitness occurred by mutation to form 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 the 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 explain the evolution strategies combined with the reinforcement learning, that is reinforcement evolution strategies. Performance of the proposed method is estimated by comparison with conventional evolution strategies on several test problems.
基于强化学习的进化策略性能改进
我们提出了一种结合强化学习的新型进化策略。我们利用突变产生的适应度变化来形成估计和控制突变步长的强化信号。该方法提高了算法的收敛速度。同时,利用柯西分布突变增强了算法的全局收敛能力。柯西分布突变比高斯分布突变更容易脱离局部极小值或偏离平台。在概述进化策略的历史之后,我们解释了与强化学习相结合的进化策略,即强化进化策略。通过与传统进化策略在若干测试问题上的比较,评估了该方法的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信