Player modeling for intelligent difficulty adjustment

In this paper we aim at automatically adjusting the difficulty of computer games by clustering players into different types and supervised pre-diction of the type from short traces of game-play. An important ingredient of video games is to challenge players by providing them with tasks of appropriate and increasing difficulty. How this difficulty should be chosen and increase over time strongly depends on the ability, experience, perception and learning curve of each individ-ual player. It is a subjective parameter that is very difficult to set. Wrong choices can eas-ily lead to players stopping to play the game as they get bored (if underburdened) or frus-trated (if overburdened). An ideal game should be able to adjust its difficulty dynamically gov-erned by the player’s performance. Modern video games utilise a game-testing process to in-vestigate among other factors the perceived dif-ficulty for a multitude of players. In this pa-per, we investigate how machine learning tech-niques can be used for automatic difficulty ad-justment. Our experiments confirm the potential of machine learning in this application.