Policy Search for Motor Primitives

Peters, J; Kober, J

Local TagsRelease HistoryDetailsSummary

Policy Search for Motor Primitives

Peters, J., & Kober, J. (2009). Policy Search for Motor Primitives. KI - Zeitschrift Künstliche Intelligenz, 23(3), 38-40.

Item is Released

show all hide all

Basic

show hide

Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-C369-5 Version Permalink: https://hdl.handle.net/21.11116/0000-0002-BE4B-5

Genre: Journal Article

Files

show Files

Locators

show

Creators

show

hide

Creators:
Peters, J^{1, 2}, Author
Kober, J^{1, 2}, Author

Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794

Content

show

hide

Free keywords: -

Abstract: Many motor skills in humanoid robotics can be learned using parametrized motor primitives from demonstrations. However, most interesting motor learning problems require self-improvement often beyond the reach of current reinforcement learning methods due to the high dimensionality of the state-space. We develop an EM-inspired algorithm applicable to complex motor learning tasks. We compare this algorithm to several well-known parametrized policy search methods and show that it outperforms them. We apply it to motor learning problems and show that it can learn the complex Ball-in-a-Cup task using a real Barrett WAM robot arm.

Details

show

hide

Language(s):

Dates: Date issued: 2009-08

Publication Status: Issued

Pages: -

Publishing info: -

Table of Contents: -

Rev. Type: -

Identifiers: BibTex Citekey: 6871

Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show

hide

Title: KI - Zeitschrift Künstliche Intelligenz

Source Genre: Journal

Creator(s):

Affiliations:

Publ. Info: -

Pages: - Volume / Issue: 23 (3) Sequence Number: - Start / End Page: 38 - 40 Identifier: -