Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents

TLDR

Current evolutionary paradigms struggle to allow subcomponents to emerge automatically, requiring computational extensions beyond hand‑designed solutions. The paper proposes an architecture that evolves interacting, coadapted subcomponents as cooperating species to solve complex problems. The architecture is implemented as a collection of cooperating species, and its effectiveness is demonstrated through a case study evolving artificial neural networks. On a string‑matching task, evolutionary pressure on the ecosystem drives the spontaneous emergence of interdependent subcomponents that span multiple niches, achieve generality, and adapt as their peers change.

Abstract

To successfully apply evolutionary algorithms to the solution of increasingly complex problems, we must develop effective techniques for evolving solutions in the form of interacting coadapted subcomponents. One of the major difficulties is finding computational extensions to our current evolutionary paradigms that will enable such subcomponents to "emerge" rather than being hand designed. In this paper, we describe an architecture for evolving such subcomponents as a collection of cooperating species. Given a simple string-matching task, we show that evolutionary pressure to increase the overall fitness of the ecosystem can provide the needed stimulus for the emergence of an appropriate number of interdependent subcomponents that cover multiple niches, evolve to an appropriate level of generality, and adapt as the number and roles of their fellow subcomponents change over time. We then explore these issues within the context of a more complicated domain through a case study involving the evolution of artificial neural networks.