EVOLUTIONARY LEARNING OF COMMUNICATING AGENTS

This paper presents the emergence of the cooperative behavior for comm unicating agents by means of Genetic Programming (GP). Our experimenta l domains are the pursuit game and the robot navigation task. We condu ct experiments with the evolution of the communicating agents and show the effectiveness of the emergent communication in terms of the robus tness of generated GP programs. The performance of GP-based multi-agen t learning is discussed with comparative experiments by using differen t breeding strategies, i.e., homogenous breeding and heterogeneous bre eding. (C) 1998 Elsevier Science Inc. All rights reserved.