Dynamic Game Difficulty Balancing in Real Time Using Evolutionary Fuzzy Cognitive Maps

Abstract

Players may cease from playing a chosen game sooner than expected for many reasons. One of the most important is related to the way game designers and developers calibrate game challenge levels. In practice, players have different skill levels and may find usual predetermined difficult levels as too easy or too hard, becoming frustrated or bored. The result may be decreased motivation to keep on playing the game, which means reduced engagement. An approach to mitigate this issue is dynamic game difficulty balancing (DGB), which is a process that adjusts gameplay parameters in real-time according to the current player skill level. In this paper we propose a real-time solution to DGB using Evolutionary Fuzzy Cognitive Maps, for dynamically balancing a game difficulty, helping to provide a well balanced level of challenge to the player. Evolutionary Fuzzy Cognitive Maps are based on concepts that represent context game variables and are related by fuzzy and probabilistic causal relationships that can be updated in real time. We discuss several simulation experiments that use our solution in a runner type game to create more engaging and dynamic game experiences.