Skip to Main Content
Adaptive Game AI improves adaptability of opponent AI as well as the challenge level of the game play; as a result the entertainment of game is augmented. The most updated algorithm of MCT (Monte-Carlo for Trees) which perform excellent in computer go can be used to achieve excellent result to control non-player characters (NPCs) in video games. In this paper, the prey and predator game genre of Dead End is used as a test-bed, the basic principle of MCT is presented, and the effectiveness of it sapplication to game AI development is demonstrated. Furthermore, by using the construction of ANN (Artificial Neural Network) trained by the data collected from Monte-Carlo Method, the validation of effectiveness and efficiency of the approach is presented. Finally, an approach of combine both the two techniques is discussed to create the intelligent adaptive game opponent.