ADAPTIVE LEARNING SYSTEMS.

Abstract

The author introduces a general class of adaptive search strategies and examines their essential properties. An application of the methodology is examined in the context of a system that learns control heuristics to govern the application of a set of problem solving operators. Performance results obtained by the system in attempting to learn to make appropriate bet decisions in the game of draw poker are presented to demonstrate the viability of the approach. Some alternative paradigms for genetic-based learning are identified and discussed.