Coevolution Learning: Synergistic Evolution of Learning Agents and Problem Representations

Lawrence Hunter

This paper describes exploratory work inspired by a recent mathematical model of genetic and cultural coevohition. In this work, a simulator implements two independent evolutionary competitions which act simultaneously on a diverse population of learning agents: one competition searches the space of free parameters of the learning agents, and the other searches the space of input representations used to characterize the training data. The simulations interact with each other indirectly, both effecting the fitness (and hence reproductive success) of agents the population. This framework simultaneously addresses several open problems in machine learning: selection of representation, integration of multiple heterogeneous learning methods into a single system, and the automated selection of learning bias appropriate for a particular problem.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.