New adaptations for evolutionary algorithm applied to dynamic difficulty adjustment system for serious game

The aim of the Dynamic Difficulty Adjustment is to dynamically balance the difficulty level of the games in order to keep the user interested in playing. Generally, a game in which the challenge level matches the skill of the human player has a greater entertainment value than a game that is either too easy (boring) or too hard (frustrating). An entertainment has an important role to play in serious games (educational games), contributing to their motivational and engaging qualities leading to players voluntarily playing serious games for extended periods of time. In this paper, we present new adaptations for reducing the number of training data for the evolutionary algorithms used to find game settings suitable for the player of a serious game. The training process for a human player should be as short as possible. Various experiments are performed. The obtained results show that the proposed adaptation causes a substantial decrease in training data for different players.