Speciation as automatic categorical modularization

An evolutionary learning system is presented which follows this second approach to automatically create a repertoire of specialist strategies for a game-playing system that relieves the human effort of deciding how to divide and specialize.

Abstract

Many natural and artificial systems use a modular approach to reduce the complexity of a set of subtasks while solving the overall problem satisfactorily. There are two distinct ways to do this. In functional modularization, the components perform very different tasks, such as subroutines of a large software project. In categorical modularization, the components perform different versions of basically the same task, such as antibodies in the immune system. This second aspect is the more natural for acquiring strategies in games of conflict, An evolutionary learning system is presented which follows this second approach to automatically create a repertoire of specialist strategies for a game-playing system. This relieves the human effort of deciding how to divide and specialize. The genetic algorithm speciation method used is one based on fitness sharing. The learning task is to play the iterated prisoner's dilemma. The learning system outperforms the tit-for-tat strategy against unseen test opponents. It learns using a "black box" simulation, with minimal prior knowledge of the learning task.