A Comparison of Genetic Programming and Look-up Table Learning for the Game of Spoof

Abstract

Many games require opponent modeling for optimal performance. The implicit learning and adaptive nature of evolutionary computation techniques offer a natural way to develop and explore models of an opponent's strategy without significant overhead. In this paper, we compare two learning techniques for strategy development in the game of Spoof, a simple guessing game of imperfect information. We compare a genetic programming approach with a look-up table based approach, contrasting the performance of each in different scenarios of the game. Results show both approaches have their advantages, but that the genetic programming approach achieves better performance in scenarios with little public information. We also trial both approaches against opponents who vary their strategy; results showing that the genetic programming approach is better able to respond to strategy changes than the look-up table based approach