A phased reinforcement learning algorithm for complex control problems

Takakuni Goto, Noriyasu Homma, Makoto Yoshizawa, Kenichi Abe

研究成果: Article査読

6 被引用数 (Scopus)

抄録

In this article, a phased reinforcement learning algorithm for controlling complex systems is proposed. The key element of the proposed algorithm is a shaping function defined on a novel position-direction space. The shaping function is autonomously constructed once the goal is reached, and constrains the exploration area to optimize the policy. The efficiency of the proposed shaping function was demonstrated by using a complex control problem of positioning a 2-link planar underactuated manipulator.

本文言語English
ページ(範囲)190-196
ページ数7
ジャーナルArtificial Life and Robotics
11
2
DOI
出版ステータスPublished - 2007 7

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Artificial Intelligence

フィンガープリント 「A phased reinforcement learning algorithm for complex control problems」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