Learning strategy fusion to acquire dynamic motion

Akihiko Yamaguchi, Jun Takamatsu, Tsukasa Ogasawara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publication2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011
Pages247-254
Number of pages8
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011 - Bled, Slovenia
Duration: 2011 Oct 262011 Oct 28

Publication series

NameIEEE-RAS International Conference on Humanoid Robots
ISSN (Print)2164-0572
ISSN (Electronic)2164-0580

Other

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

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Human-Computer Interaction
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Learning strategy fusion to acquire dynamic motion'. Together they form a unique fingerprint.

Cite this