Resource Sharing and Coevolution in Evolving Cellular Automata

Evolving one-dimensional cellular automata (CAs) with genetic algorithms has provided insight into how improved performance on a task requiring global coordination emerges when only local interactions are possible. Two approaches that can affect the search efficiency of the genetic algorithm are coevolution, in which a population of problems--in our case, initial configurations of the CA lattice--evolves along with the population of CAs; and resource sharing, in which a greater proportion of a limited fitness resource is assigned to those CAs which correctly solve problems that fewer other CAs in the population can solve. Here we present evidence that, in contrast to what has been suggested elsewhere, the improvements observed when both techniques are used together depend largely on resource sharing alone.