A Replicator Dynamics Analysis of Difference Evaluation Functions

A key difficulty in Cooperative Coevolutionary Algorithms (CCEAs) is the credit assignment problem[1]. One solution to the credit assignment problem is the difference evaluation function, which produces excellent results in many multiagent domains. However, to date, there has been no prescriptive theoretical analysis deriving conditions under which difference evaluations improve the probability of selecting optimal actions. In this paper, we derive such conditions.