Learning arm's posture control using reinforcement learning and feedback-error-learning.

Full Abstract

In this paper, we propose a learning model using the Actor-Critic method and the feedback-error-learning scheme. The Actor-Critic method, which is one of the major frameworks in reinforcement learning, has attracted attention as a computational learning model in the basal ganglia. Meanwhile, the feedback-error-learning is learning architecture proposed as a computationally coherent model of cerebellar motor learning. This learning architecture's purpose is to acquire a feed-forward controller by using a feedback controller's output as an error signal. In past researches, a predetermined constant gain feedback controller was used for the feedback-error-learning. We use the Actor-Critic method for obtaining a feedback controller in the feedback-error-earning. By applying the proposed learning model to an arm's posture control, we show that high-performance feedback and feed-forward controller can be acquired from only by using a scalar value of reward.

Learn Faster Today Improve your study skills

Author information

Author/s: Kambara, H (H); Kim, J (J); Sato, M (M); Koike, Y (Y);

Affiliation: Dept. of Comput. Intelligence & Syst. Sci., Interdisciplinary Graduate School of Science and Engineering, Tokyo Inst. of Technol., Japan.

Journal and publication information

Publication Type: Journal Article

Journal: Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference (Conf Proc IEEE Eng Med Biol Soc), published in United States. (Language: eng)

Reference: 2004-; vol 1 (issue ) : pp 486-9

Dates: Created 2007/02/02; Completed 2007/05/17;

PMID: 17271719, status: PubMed-not-MEDLINE (last retrieval date: 12/26/2008)

Sourced from the National Library of Medicine. Abstract text and other information may be subject to copyright.

External Links for this article (including full text providers, if available):

Click Electronic Full-text Provider Links to see options for finding the electronic full text links to this article. Note there may be a subscription or fee required for access to the full text. See our FAQ for information on finding FREE full text articles.

This article may also be located in paper journal collections available in many libraries. Use the Journal and Publication Information above to find the full article.

MeSH headings (categories)

This article was linked to the MESH Headings shown below.

No MeSH Headings found.

The article may not be MeSH Indexed as yet.

This article has not been indexed for related articles as yet, however you can still use the live related article search links below.

See 100+ related articles.