Challenges for the policy representation when applying reinforcement learning in robotics

File Description SizeFormat 
Kormushev_IJCNN-2012.pdfAccepted version1.93 MBAdobe PDFView/Open
Title: Challenges for the policy representation when applying reinforcement learning in robotics
Authors: Kormushev, P
Calinon, S
Ugurlu, B
Caldwell, DG
Item Type: Conference Paper
Abstract: A summary of the state-of-the-art reinforcement learning in robotics is given, in terms of both algorithms and policy representations. Numerous challenges faced by the policy representation in robotics are identified. Two recent examples for application of reinforcement learning to robots are described: pancake flipping task and bipedal walking energy minimization task. In both examples, a state-of-the-art Expectation-Maximization-based reinforcement learning algorithm is used, but different policy representations are proposed and evaluated for each task. The two proposed policy representations offer viable solutions to four rarely-addressed challenges in policy representations: correlations, adaptability, multi-resolution, and globality. Both the successes and the practical difficulties encountered in these examples are discussed. © 2012 IEEE.
Issue Date: 10-Jun-2012
Date of Acceptance: 10-Jun-2012
ISBN: 978-1-4673-1488-6
ISSN: 2161-4393
Publisher: IEEE
Start Page: 1
End Page: 8
Journal / Book Title: The 2012 International Joint Conference on Neural Networks (IJCNN)
Copyright Statement: © 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Conference Name: The 2012 International Joint Conference on Neural Networks (IJCNN)
Publication Status: Published
Publisher URL:
Start Date: 2012-06-10
Finish Date: 2015-06-15
Conference Place: Brisbane, Australia
Appears in Collections:Dyson School of Design Engineering

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx