Robot Reinforcement Learning Based on Learning Classifier System (original) (raw)

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 easily reduce learning space, improve online learning ability and robustness.

Preview

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Baneamoon, S.M., Abdul Salam, R.: Bucket Brigade Algorithm Enhancement for Robot Behaviors. In: International Conference on Robotics, Vision, Information and Signal Processing (ROVISP 2007), Penang, Malaysia, November 28-30, pp. 930–934 (2007)
    Google Scholar
  2. Glorennec, P.Y.: Reinforcement Learning: An Overview. In: Eur. Symp. Intell. Tech., Aachen, Germany, pp. 17–35 (2000)
    Google Scholar
  3. Wang, Y., Huber, M., Papudesi, V.N., Cook, D.J.: User-guided Reinforcement Learning of Robot Assistive Tasks For an Intelligent Environment. In: Proc. IEEE/RJS Int. Conf. Intell. Robots Syst., vol. 1, pp. 424–429 (2003)
    Google Scholar
  4. Bull, L., Kovacs, T.: Foundations of Learning Classifier Systems: An Introduction. In: Foundations of Learning Classifier Systems, vol. 183, pp. 1–17. Springer, New York (2005)
    Chapter Google Scholar
  5. Enhancement for Robot Behaviors. International Journal of Intelligent Technology 2(3), 172–177 (2007), ISSN 1305-6417
    Google Scholar
  6. Musilek, P., Li, S., Wyard-Scot, L.: Enhanced Learning ClassifierSystem for Robot Navigation. In: IROS 2005, IEEE/RSJ International Conference on Intelligent Robots and Systems, Alberta, Canada, pp. 3390–3395 (2005)
    Google Scholar
  7. Bull, L., Studley, M., Bagnall, A., Whittley, I.: Learing Classifier System Ensembles With Rule-sharing. IEEE Transactions on Evolutionary Computation 4 (2007)
    Google Scholar
  8. Bay, S.J.: Learning Classifier Systems for Single and Multiple Mobile Robots in Unstructured Environments. In: Mobile Robots X, Philadelphia, PA, pp. 88–99 (1995)
    Google Scholar

Download references

Author information

Authors and Affiliations

  1. School of computer Science & Technology, Nanjing University of Science & Technology, Nanjing, 210094, P.R. China
    Jie Shao & Jing-yu Yang

Authors

  1. Jie Shao
  2. Jing-yu Yang

Editor information

Editors and Affiliations

  1. Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, Anhui,, China
    De-Shuang Huang
  2. School of Computing and Intelligent Systems, University of Ulster at Magee Campus, BT48 7JL, Derry, Northern Ireland, UK
    Martin McGinnity
  3. Laboratoire LITIS, Université de Rouen, 76800, Saint Etienne du Rouvray, France
    Laurent Heutte
  4. Department of Electrical and Computer Engineering, Ryerson University, Toronto, Ontario, Canada
    Xiao-Ping Zhang

Rights and permissions

© 2010 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Shao, J., Yang, Jy. (2010). Robot Reinforcement Learning Based on Learning Classifier System. In: Huang, DS., McGinnity, M., Heutte, L., Zhang, XP. (eds) Advanced Intelligent Computing Theories and Applications. ICIC 2010. Communications in Computer and Information Science, vol 93. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-14831-6\_27

Download citation

Keywords

Publish with us