K.S.Y. Chiu and K.C.C. Chan (PRC)
Artificial intelligence, Game Development, Data Mining
A balanced game provides a satisfying level of challenge. This can be done using traditional game programs and artificial intelligent (AI) techniques but more researchers are aiming for dynamic game balancing which uses reinforcement learning and focuses on the movement of non-player characters, especially in scripted games. However, this is not suitable for all game genres, such as those that use mazes that require dynamic terrains. We propose mining data for sequential patterns that can be used to analyze a player’s behaviors and then use this data to adjust the level of difficulty of a game. Our method first mines individual gameplay data and then transforms it into a set of sequential patterns. This proposed approach differs from existing rule-based Game AI algorithms in three ways: (1) the game levels are based on the past experience of the player; (2) the approach is data-driven; (3) the game levels are not predefined, making them more adaptive, more interesting and balanced. This approach is tested here on a maze game. Feedback from participants in our experiments was very positive as they found the games designed using the proposed approach to be both more interesting and more balanced.
Important Links:
Go Back
