Self-Organization of Communication in Distributed Learning Classifier Systems

In this paper, an application of learning classifier systems is presented. An artificial multi-agent environment has been designed. Mate finding problem, a learning task inspired by nature, is considered which needs cooperation by two distinct agents to achieve the goal. The main feature of our system is existence of two parallel learning subsystems which have to agree on a common communication protocol to succeed in accomplishing the task. Apart from standard learning algorithms, a unification mechanism has been introduced to encourage coordinated behavior among the agents belonging to the same class. Experimental results are presented which demonstrate the effectiveness of this mechanism and the learning capabilities of classifier systems.