Learning fuzzy classifier systems for multi-agent coordination

We present ELF, a learning fuzzy classifier system (LFCS), and its applicat ion to the field of Learning Autonomous Agents. In particular, we will show how this kind of Reinforcement Learning systems can be successfully applie d to learn both behaviors and their coordination for Autonomous Agents. We will discuss the importance of knowledge representation approach based on f uzzy sets to reduce the search space without losing the required precision. Moreover, we will show how we have applied ELF to learn the distributed co ordination among agents which can exchange information with each other. The experimental validation has been done on software agents interacting in a real-time task. (C) 2001 Elsevier Science Inc. All rights reserved.