Abstract
We study behavioural patterns learned by a robotic agent by means of two different control and adaptive approaches — a radial basis function neural network trained by evolutionary algorithm, and a traditional reinforcement Q-learning algorithm. In both cases, a set of rules controlling the agent is derived from the learned controllers, and these sets are compared. It is shown that both procedures lead to reasonable and compact, albeit rather different, rule sets.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Pfeifer, R., Scheier, C.: Understanding Intelligence. The MIT Press, Cambridge (2000)
Sutton, S.R., Barto, G.A.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (1998)
Nolfi, S., Floreano, D.: Evolutionary Robotics — The Biology, Intelligence and Techology of Self-Organizing Machines. The MIT Press, Cambridge (2000)
Holland, J.: Adaptation In Natural and Artificial Systems. MIT Press, Cambridge (1992)
Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn. Prentice Hall, Englewood Cliffs (1999)
Slušný, S., Neruda, R.: Evolving Homing Behaviour for Team of Robots. Computational Intelligence, Robotics and Autonomous Systems. Massey University, Palmerston North (2007)
Slušný, S., Neruda, R., Vidnerová, P.: Evolution of Simple Behavior Patterns for Autonomous Robotic Agent. System Science and Simulation in Engineering, pp. 411–417. WSEAS Press (2007)
Watkins, C.J.C.H.: Learning from Delayed Rewards. Ph.D. thesis (1989)
Mitchell, T.: Machine Learning. McGraw Hill, New York (1997)
Poggio, T., Girosi, F.: A Theory of Networks for Approximation and Learning. Technical report, A. I. Memo No. 1140, C.B.I.P. Paper No.31, Massachusetts Institute of Technology, Cambridge, MA, USA (1989)
Moody, J., Darken, C.: Fast Learning in Networks of Locally-tuned Processing Units. Neural Computation 1, 289–303 (1989)
Broomhead, D., Lowe, D.: Multivariable Functional Interpolation and Adaptive Networks. Complex Systems 2, 321–355 (1988)
Fogel, D.: Evolutionary Computation: The Fossil Record. MIT-IEEE Press (1998)
E-puck, online documentation, http://www.e-puck.org
Webots simulator on-line documentation, http://www.cyberbotics.com/
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Slušný, S., Neruda, R., Vidnerová, P. (2008). Rule-Based Analysis of Behaviour Learned by Evolutionary and Reinforcement Algorithms. In: Huang, DS., Wunsch, D.C., Levine, D.S., Jo, KH. (eds) Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence. ICIC 2008. Lecture Notes in Computer Science(), vol 5227. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-85984-0_35
Download citation
DOI: https://doi.org/10.1007/978-3-540-85984-0_35
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-85983-3
Online ISBN: 978-3-540-85984-0
eBook Packages: Computer ScienceComputer Science (R0)