Communications of the ACM
Scientists Develop Model That Adjusts Videogame Difficulty Based on Player Emotions
DDA agents tailor the AI opponent's behavior to improve the player's experience.
Credit: GIST
A research team from the Gwangju Institute of Science and Technology in Korea put a twist on dynamic difficulty adjustment (DDA), a method of modifying a videogame in real-time, according to a study published in Expert Systems With Applications. Instead of focusing on the player's performance, they developed DDA agents that adjust a game's difficulty to maximize one of four different aspects related to a player's satisfaction.
The DDA agents were trained via machine learning using data gathered from actual human players, who played a fighting game against various artificial intelligences and then answered a questionnaire about their experience.
Using a Monte-Carlo tree search algorithm, each DDA agent employed game data and simulated data to tune the opposing AI's fighting style in a way that maximized a specific emotion, or "affective state."
The team verified that the proposed DDA agents could produce AIs that improved the players' overall experience. The incorporation of affective states into DDA agents could be useful for commercial games. "Game companies . . . can exploit these data to model the players and solve various issues related to game balancing using our approach," says Associate Professor Kyung-Joong Kim, who led the study.
From Gwangju Institute of Science and Technology
View Full Article
No entries found