Learning strategy fusion to acquire dynamic motion

Akihiko Yamaguchi, Jun Takamatsu, Tsukasa Ogasawara

研究成果: Conference contribution

5 被引用数 (Scopus)

抄録

This paper proposes a method to fuse learning strategies (LSs) in a reinforcement learning framework. In this method, some LSs are integrated for learning a single task of a single robot. The LSs consists of (1) LS-scratch: learning a policy from scratch, (2) LS-accelerating: learning a policy from a previously learned policy by accelerating motion-speed parameters, and (3) LS-freeing: learning a policy from a previously learned policy by increasing the DoF (degree of freedom). The proposed LS fusion method enables (A) in the early stage of learning, LS fusion can select a suitable DoF configuration from a predefined set of DoF configurations, and (B) after a behavior module that learns from scratch converges, the LSs are applied to improve the policy. As a result, a robot can learn a complex task by starting with a simplified configuration, and then transferring the learned behaviors while increasing the difficulty. We introduce WF-DCOB proposed by Yamaguchi et al. for the LSs. We verify the proposed LS fusion method with a crawling task of a humanoid robot. The simulation experiments demonstrate the advantage of the proposed method compared to learning with a single learning module.

本文言語English
ホスト出版物のタイトル2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011
ページ247-254
ページ数8
DOI
出版ステータスPublished - 2011
外部発表はい
イベント2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011 - Bled, Slovenia
継続期間: 2011 10 262011 10 28

出版物シリーズ

名前IEEE-RAS International Conference on Humanoid Robots
ISSN(印刷版)2164-0572
ISSN(電子版)2164-0580

Other

Other2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011
国/地域Slovenia
CityBled
Period11/10/2611/10/28

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ ビジョンおよびパターン認識
  • ハードウェアとアーキテクチャ
  • 人間とコンピュータの相互作用
  • 電子工学および電気工学

フィンガープリント

「Learning strategy fusion to acquire dynamic motion」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