Learning to compose fuzzy behaviors for autonomous agents☆

https://doi.org/10.1016/S0888-613X(97)00002-9Get rights and content
Under an Elsevier user license
open archive

Abstract

We present S-ELF, an evolutionary algorithm that we have developed to learn the context of activation of fuzzy logic controllers implementing fuzzy behaviors for an autonomous agent. S-ELF learns context metarules that are used to coordinate basic behaviors in order to perform complex tasks in a partially and imprecisely known environment. Context metarules are expressed in terms of positive and negated fuzzy predicates. We also show how S-ELF can learn robust and portable behaviors, thus reducing the time and effort to design behavior-based agents.

Keywords

reinforcement learning
fuzzy control
autonomous agents

Cited by (0)

☆

We would like to thank A. Saffiotti, who suggested important issues during interesting discussions. This work has been partially supported by the MURST Project 60% “Development of autonomous agents through machine learning.”

Copyright © 1997 Published by Elsevier Inc.