Evolutionary Design of a Rule-Changing Artificial Society Using Genetic Algorithms

In this paper we address an artificial society in which action rules change with time. We propose a new method to design the action rules of agents in artificial society that can satisfy specified requests by using genetic algorithms (GAs). In the proposed method, each chromosome in the GA population represents a candidate set of action rules and the number of rule iterations. While the usual method applies rules in order of precedence, the present method applies a set of rules repeatedly for a certain period. Experimental results obtained using an artificial society show that the proposed method is more efficient than the usual method.