Learning to compose fuzzy behaviors for autonomous agents

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.