形态学与控制协同进化的过早收敛性研究

IF 1.2 4区 计算机科学 Q4 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Adaptive Behavior Pub Date : 2023-09-07 DOI:10.1177/10597123231198497
Luis Eguiarte-Morett, Wendy Aguilar
{"title":"形态学与控制协同进化的过早收敛性研究","authors":"Luis Eguiarte-Morett, Wendy Aguilar","doi":"10.1177/10597123231198497","DOIUrl":null,"url":null,"abstract":"This article addresses the co-evolution of morphology and control in evolutionary robotics, focusing on the challenge of premature convergence and limited morphological diversity. We conduct a comparative analysis of state-of-the-art algorithms, focusing on QD (Quality-Diversity) algorithms, based on a well-defined methodology for benchmarking evolutionary algorithms. We introduce carefully chosen indicators to evaluate their performance in three core aspects: task performance, phenotype diversity, and genotype diversity. Our findings highlight MNSLC (Multi-BC NSLC), with the introduction of aligned novelty to NSLC (Novelty Search with Local Competition), as the most effective algorithm for diversity preservation (genotype and phenotype diversity), while maintaining a competitive level of exploitability (task performance). MAP-Elites, although exhibiting a well-balanced trade-off between exploitation and exploration, fall short in protecting morphological diversity. NSLC, while showing similar performance to MNSLC in terms of exploration, is the least performant in terms of exploitation, contrasting with QN (Fitness-Novelty MOEA), which exhibits much superior exploitation, but inferior exploration, highlighting the effects of local competition in skewing the balance toward exploration. Our study provides valuable insights into the advantages, disadvantages, and trade-offs of different algorithms in co-evolving morphology and control.","PeriodicalId":55552,"journal":{"name":"Adaptive Behavior","volume":" ","pages":""},"PeriodicalIF":1.2000,"publicationDate":"2023-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Premature convergence in morphology and control co-evolution: a study\",\"authors\":\"Luis Eguiarte-Morett, Wendy Aguilar\",\"doi\":\"10.1177/10597123231198497\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This article addresses the co-evolution of morphology and control in evolutionary robotics, focusing on the challenge of premature convergence and limited morphological diversity. We conduct a comparative analysis of state-of-the-art algorithms, focusing on QD (Quality-Diversity) algorithms, based on a well-defined methodology for benchmarking evolutionary algorithms. We introduce carefully chosen indicators to evaluate their performance in three core aspects: task performance, phenotype diversity, and genotype diversity. Our findings highlight MNSLC (Multi-BC NSLC), with the introduction of aligned novelty to NSLC (Novelty Search with Local Competition), as the most effective algorithm for diversity preservation (genotype and phenotype diversity), while maintaining a competitive level of exploitability (task performance). MAP-Elites, although exhibiting a well-balanced trade-off between exploitation and exploration, fall short in protecting morphological diversity. NSLC, while showing similar performance to MNSLC in terms of exploration, is the least performant in terms of exploitation, contrasting with QN (Fitness-Novelty MOEA), which exhibits much superior exploitation, but inferior exploration, highlighting the effects of local competition in skewing the balance toward exploration. Our study provides valuable insights into the advantages, disadvantages, and trade-offs of different algorithms in co-evolving morphology and control.\",\"PeriodicalId\":55552,\"journal\":{\"name\":\"Adaptive Behavior\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":1.2000,\"publicationDate\":\"2023-09-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Adaptive Behavior\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1177/10597123231198497\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Adaptive Behavior","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1177/10597123231198497","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

本文讨论了进化机器人中形态学和控制的协同进化,重点讨论了过早收敛和形态学多样性有限的挑战。我们对最先进的算法进行了比较分析,重点是QD(质量多样性)算法,基于一种定义良好的基准进化算法方法。我们引入了精心选择的指标来评估他们在三个核心方面的表现:任务表现、表型多样性和基因型多样性。我们的研究结果突出了MNSLC(Multi-BC-NSLC),它在NSLC(具有局部竞争的新颖性搜索)中引入了一致的新颖性,是保持多样性(基因型和表型多样性)的最有效算法,同时保持了竞争水平的可利用性(任务性能)。MAP精英虽然在开发和勘探之间表现出了良好的平衡,但在保护形态多样性方面做得不够。NSLC虽然在勘探方面表现出与MNSLC相似的表现,但在开发方面表现最差,与QN(Fitness Novelty MOEA)形成鲜明对比,后者表现出更优越的开发,但勘探较差,突出了当地竞争对勘探平衡的影响。我们的研究为不同算法在协同进化形态和控制中的优势、劣势和权衡提供了有价值的见解。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Premature convergence in morphology and control co-evolution: a study
This article addresses the co-evolution of morphology and control in evolutionary robotics, focusing on the challenge of premature convergence and limited morphological diversity. We conduct a comparative analysis of state-of-the-art algorithms, focusing on QD (Quality-Diversity) algorithms, based on a well-defined methodology for benchmarking evolutionary algorithms. We introduce carefully chosen indicators to evaluate their performance in three core aspects: task performance, phenotype diversity, and genotype diversity. Our findings highlight MNSLC (Multi-BC NSLC), with the introduction of aligned novelty to NSLC (Novelty Search with Local Competition), as the most effective algorithm for diversity preservation (genotype and phenotype diversity), while maintaining a competitive level of exploitability (task performance). MAP-Elites, although exhibiting a well-balanced trade-off between exploitation and exploration, fall short in protecting morphological diversity. NSLC, while showing similar performance to MNSLC in terms of exploration, is the least performant in terms of exploitation, contrasting with QN (Fitness-Novelty MOEA), which exhibits much superior exploitation, but inferior exploration, highlighting the effects of local competition in skewing the balance toward exploration. Our study provides valuable insights into the advantages, disadvantages, and trade-offs of different algorithms in co-evolving morphology and control.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Adaptive Behavior
Adaptive Behavior 工程技术-计算机:人工智能
CiteScore
4.30
自引率
18.80%
发文量
34
审稿时长
>12 weeks
期刊介绍: _Adaptive Behavior_ publishes articles on adaptive behaviour in living organisms and autonomous artificial systems. The official journal of the _International Society of Adaptive Behavior_, _Adaptive Behavior_, addresses topics such as perception and motor control, embodied cognition, learning and evolution, neural mechanisms, artificial intelligence, behavioral sequences, motivation and emotion, characterization of environments, decision making, collective and social behavior, navigation, foraging, communication and signalling. Print ISSN: 1059-7123
期刊最新文献
Environmental complexity, cognition, and plant stress physiology A model of how hierarchical representations constructed in the hippocampus are used to navigate through space Mechanical Problem Solving in Goffin’s Cockatoos—Towards Modeling Complex Behavior Coupling First-Person Cognitive Research With Neurophilosophy and Enactivism: An Outline of Arguments The origin and function of external representations
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1