Robot Reinforcement Learning Based on LCS-GDM

Yong Bin Ma

doi:10.4028/www.scientific.net/AMM.347-350.416

Paper Titles

Study on the Application of Virtual Prototyping Technology to UAV Fault Diagnosis Training
p.396

The Application of Model Reference ADRC Based on PD Gain Adaptive Regulation in Quadrotor UAV
p.401

Research on AS/RS Simulation Based on Flexsim
p.406

Study of Measuring Velocity Based on Double-Signal System
p.411

Robot Reinforcement Learning Based on LCS-GDM
p.416

Localization of the Sound Source Based on Directional Orthogonal Periodic Wavelet Basis
p.421

A New Rotor Fault Diagnosis Method Based on EEMD Sample Entropy and Grey Relation Degree
p.426

Application of EEMD Energy Distribution and Grey Incidence in Gearbox Fault Diagnosis
p.430

The Design of an Electric Bicycle Controller Based on Programmable System on Chip
p.434

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 347-350Robot Reinforcement Learning Based on LCS-GDM

Robot Reinforcement Learning Based on LCS-GDM

Abstract:

This paper proposed a robot reinforcement learning method based on learning classifier system. A learning Classifier System is a rule-based machine learning system that combines reinforcement learning and genetic algorithms. The reinforcement learning component is responsible for adjusting the strength of rules in the system according to some reward obtained from the environment. The genetic algorithm acts as an innovation discovery component which is responsible for discovering new better learning rules. The advantages of this approach are its rule-based representation, which can be easily reduce learning space, online learning ability, robustness .

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 347-350)

Pages:

416-420

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.347-350.416

Citation:

Cite this paper

Online since:

August 2013

Authors:

Yong Bin Ma

Keywords:

Genetic Algorithm (GA), Gradient Deescent Methods (GDM), Learning Classifier System (LCS), Reinforcement Learning, Robot

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] S. M. Baneamoon, R. Abdul Salam, Bucket Brigade Algorithm Enhancement for Robot Behaviors , International Conference on Robotics, Vision, Information and Signal Processing (ROVISP 2007), Penang, Malaysia, 28-30 November 2007, pp.930-934.

Google Scholar

[2] P. Y. Glorennec, Reinforcement learning: An overview, in Eur. Symp. Intell. Tech., Aachen, Germany, 2000, p.17–35.

Google Scholar

[3] Y. Wang, M. Huber, V. N. Papudesi, and D. J. Cook, User-guided reinforcement learning of robot assistive tasks for an intelligent environment, in Proc. IEEE/RJS Int. Conf. Intell. Robots Syst., 2003, vol. 1, p.424–429.

DOI: 10.1109/iros.2003.1250666

Google Scholar

[4] L. Bull and T. Kovacs, Foundations of learning classifier systems: An introduction, in Foundations of Learning Classifier Systems. New York: Springer-Verlag, 2005, vol. 183, p.1–17.

DOI: 10.1007/11319122_1

Google Scholar

[5] Enhancement for Robot Behaviors", International Journal of Intelligent Technology, Volume 2 Number 3, ISSN 1305-6417, 2007, pp.172-177.

Google Scholar

[6] P. Musilek, Sa Li, and L. Wyard-Scot, Enhanced Learning ClassifierSystem for Robot Navigation , IROS 2005, IEEE/RSJ International Conference on Intelligent Robots and Systems, Alberta, Canada, 2-6Aug. 2005, pp.3390-3395.

DOI: 10.1109/iros.2005.1545150

Google Scholar

[7] Larry bull, Mattew studley, AnthonyBagnall, Ian whittley. Learing classifier system ensembles with rule-sharing. IEEE transactions on evolutionary computation, Vol, No. 4, august (2007).

DOI: 10.1109/tevc.2006.885163

Google Scholar

[8] S. J. Bay, Learning Classifier Systems for Single and Multiple Mobile Robots in Unstructured Environments, Mobile Robots X. Philadelphia, PA, Nov. 1995, pp.88-99.

DOI: 10.1117/12.228965

Google Scholar