Sustaining behavioral diversity in NEAT

Hirotaka Moriguchi, Shinichi Honiden*

*この研究の対応する著者

研究成果: Conference contribution

8 被引用数 (Scopus)

抄録

Niching schemes, which sustains population diversity and let an evolutionary population avoid premature convergence, have been extensively studied in the research field of evolutionary algorithms. Neuroevolutionary (NE) algorithms, such as NEAT, have also benefitted from niching. However, the latest research indicates that the use of genotypeor phenotype-similarity-based niching schemes in NE algorithms is not highly effective because these schemes have difficulty sustaining the behavioral diversity in the environment. In this paper, we propose a novel niching scheme that takes into consideration both the phenotypic and behavioral diversity, and then integrate it with NEAT. An experimental analysis revealed that the proposed algorithm outperforms the original NEAT for various problem settings. More interestingly, it performs especially well for problems with a high noise level and large state space. Since these features are common in problems to which NEAT is applied, the proposed algorithm should be effective in practice.

本文言語English
ホスト出版物のタイトルProceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10
ページ611-618
ページ数8
DOI
出版ステータスPublished - 2010 8 27
外部発表はい
イベント12th Annual Genetic and Evolutionary Computation Conference, GECCO-2010 - Portland, OR, United States
継続期間: 2010 7 72010 7 11

出版物シリーズ

名前Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10

Conference

Conference12th Annual Genetic and Evolutionary Computation Conference, GECCO-2010
国/地域United States
CityPortland, OR
Period10/7/710/7/11

ASJC Scopus subject areas

  • 計算理論と計算数学
  • 理論的コンピュータサイエンス

フィンガープリント

「Sustaining behavioral diversity in NEAT」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル