Back to the program.
An exploration on the evolution of learning behaviour using robot based models
Elio Tuci
IRIDIA
etuci@ulb.ac.be

Abstract

I present some work I have done during my PhD, which concerns the study of the evolution of simple forms of learning behaviour in artificial agents. I firstly claim that agent-based models are a complementary methodological tool to investigate issues concerning the evolution of learning in natural systems. Then, I support my claim by showing the results of simulations which focus on the study of the nature of the selection pressures and the "ecology" of the artificial system which facilitate the evolution of simple form of associative learning.

Keywords

Evolutionary Robotics, evolution of learning, neural network

References

  1. Tuci E., Quinn M., Harvey I.. (2003) An evolutionary ecological approach to the study of learning behaviour using a robot based model, Adaptive Behavior, 10:201--221.