Sample efficiency improvement on neuroevolution via estimation-based elimination strategy

Shengbo Xu, Yuki Inoue, Tetsunari Inamura, Hirotaka Moriguchi, Shinichi Honiden

研究成果: Conference contribution

抄録

In this paper, we propose estimation-based elimination strategy, which improves sample efficiency of NeuroEvolution (NE) algorithms. The fitness of new individuals was estimated using fitness of individuals evaluated in the past generations. The estimation was achieved by taking average fitness of individuals with high correlation with the new individual. Estimation-based elimination strategy avoids evaluating individuals with low estimated fitness. We adapt estimation-based elimination strategy for state-of-the-art NE algorithms: CMA-NeuroES and CMA-TWEANN. From the experimental results of pole-balancing benchmark tasks, we show that the proposed strategy improves sample efficiency of the NE algorithms.

本文言語English
ホスト出版物のタイトル13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014
出版社International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
ページ1537-1538
ページ数2
ISBN(電子版)9781634391313
出版ステータスPublished - 2014
外部発表はい
イベント13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014 - Paris, France
継続期間: 2014 5月 52014 5月 9

出版物シリーズ

名前13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014
2

Conference

Conference13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014
国/地域France
CityParis
Period14/5/514/5/9

ASJC Scopus subject areas

  • 人工知能

フィンガープリント

「Sample efficiency improvement on neuroevolution via estimation-based elimination strategy」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