Comparison of RBF Network Learning and Reinforcement Learning on the Maze Exploration Problem (original) (raw)

Abstract

An emergence of intelligent behavior within a simple robotic agent is studied in this paper. Two control mechanisms for an agent are considered — a radial basis function neural network trained by evolutionary algorithm, and a traditional reinforcement learning algorithm over a finite agent state space. A comparison of these two approaches is presented on the maze exploration problem.

Preview

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Broomhead, D.S., Lowe, D.: Multivariable functional interpolation and adaptive networks. Complex Systems 2, 321–355 (1988)
    MATH MathSciNet Google Scholar
  2. E-puck, online documentation, http://www.e-puck.org
  3. Fogel, D.B.: Evolutionary Computation: The Fossil Record. MIT/ IEEE Press (1998)
    Google Scholar
  4. Haykin, S.: Neural Networks: a comprehensive foundation, 2nd edn. Prentice-Hall, Englewood Cliffs (1999)
    MATH Google Scholar
  5. Holland, J.: Adaptation In Natural and Artificial Systems. MIT Press, Cambridge (1992)
    Google Scholar
  6. Mitchell, T.: Machine Learning. McGraw-Hill, New York (1997)
    MATH Google Scholar
  7. Moody, J., Darken, C.: Fast learning in networks of locally-tuned processing units. Neural Computation 1, 289–303 (1989)
    Article Google Scholar
  8. Nolfi, S., Floreano, D.: Evolutionary Robotics — The Biology, Intelligence and Techology of Self-Organizing Machines. MIT Press, Cambridge (2000)
    Google Scholar
  9. Pfeifer, R., Scheier, C.: Understanding Intelligence. MIT Press, Cambridge (2000)
    Google Scholar
  10. Poggio, T., Girosi, F.: A theory of networks for approximation and learning. Technical report, Massachusetts Institute of Technology, Cambridge, MA, USA, A. I. Memo No. 1140, C.B.I.P. Paper No. 31 (1989)
    Google Scholar
  11. Slušný, S., Neruda, R.: Evolving homing behaviour for team of robots. In: Computational Intelligence, Robotics and Autonomous Systems. Massey University, Palmerston North (2007)
    Google Scholar
  12. Slušný, S., Neruda, R., Vidnerová, P.: Evolution of simple behavior patterns for autonomous robotic agent. In: System Science and Simulation in Engineering, pp. 411–417. WSEAS Press (2007)
    Google Scholar
  13. Richard Sutton, S., Andrew Barto, G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
    Google Scholar
  14. Watkins, C.J.C.H.: Learning from delayed rewards. Ph.D. thesis (1989)
    Google Scholar
  15. Webots simulator. On-line documentation, http://www.cyberbotics.com/

Download references

Author information

Authors and Affiliations

  1. Institute of Computer Science, Academy of Sciences of the Czech Republic, Pod vodárenskou věží 2, Prague 8, Czech Republic
    Stanislav Slušný, Roman Neruda & Petra Vidnerová

Authors

  1. Stanislav Slušný
  2. Roman Neruda
  3. Petra Vidnerová

Editor information

Véra Kůrková Roman Neruda Jan Koutník

Rights and permissions

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Slušný, S., Neruda, R., Vidnerová, P. (2008). Comparison of RBF Network Learning and Reinforcement Learning on the Maze Exploration Problem. In: Kůrková, V., Neruda, R., Koutník, J. (eds) Artificial Neural Networks - ICANN 2008. ICANN 2008. Lecture Notes in Computer Science, vol 5163. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87536-9\_74

Download citation

Keywords

These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Publish with us