GAME PLAYER STRATEGY PATTERN RECOGNITION BY USING K-NEAREST NEIGHBOR

Pattern recognition has been successfully used in different application areas, its application on identifying player's strategy during the gameplay which is called Player Strategy Pattern Recognition (PSPR), is another interesting area. PSPR can greatly improve game AI's adaptability, and as a result the entertainment of game is promoted. In this paper, Pac-Man game is used as a test-bed. Classifier of k-nearest neighbor (KNN) algorithm is chosen to analyze off-line data from gamers who are choosing different strategies, in other words the classifiers are trained with sample data from players using different strategies. The method attempts to use the trained classifier to predict strategy pattern of a future player based on the data captured from its gameplay. This paper presents the basic principle of the PSPR by using the KNN theoretic approach and discusses the results of the experiments.