Sample efficiency analysis of Neuroevolution algorithms on a quadruped robot

Shengbo Xu, Hirotaka Moriguch, Shinichi Honiden

研究成果: Conference contribution

4 被引用数 (Scopus)

抄録

In reinforcement learning tasks with continuous state-action, parameterized policy search has been known to be a powerful method. Applying NeuroEvolution (NE) to optimizing the policy represented by artificial neural network (ANN) is a particularly active research field. In most cases, NE algorithms cost a large amount of trial-and-error (episode) to optimize policies. However, due to time and cost constraints, researchers and practitioners cannot repeat a number of episodes on physical robots. Thus, choosing an efficient NE algorithm is a key to optimize policies with limited time and cost. In this work, our goal is to help users to choose an efficient NE algorithm. We compare and analyze sample efficiency of two successful state-of-the-art NE algorithms: CMA-NeuroES and NEAT in a gait generation task of a quadruped robot. Moreover, we run both algorithms with various initial topologies in order to analyze the performance difference between each topology. From experimental results, we show CMA-NeuroES outperforms NEAT regardless of initial topologies when the limited number of episodes can be executed. Additional experiments conclude that the optimization method for connection weights in NEAT results in its inferior performance to CMA-NeuroES, while a probability-weighted averaging characteristic and self-adaptive factors make CMA-NeuroES to be advantageous.

本文言語English
ホスト出版物のタイトル2013 IEEE Congress on Evolutionary Computation, CEC 2013
ページ2170-2177
ページ数8
DOI
出版ステータスPublished - 2013 8 21
外部発表はい
イベント2013 IEEE Congress on Evolutionary Computation, CEC 2013 - Cancun, Mexico
継続期間: 2013 6 202013 6 23

出版物シリーズ

名前2013 IEEE Congress on Evolutionary Computation, CEC 2013

Other

Other2013 IEEE Congress on Evolutionary Computation, CEC 2013
国/地域Mexico
CityCancun
Period13/6/2013/6/23

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

「Sample efficiency analysis of Neuroevolution algorithms on a quadruped robot」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