DL-DDA -- Deep Learning based Dynamic Difficulty Adjustment with UX and Gameplay constraints
This addresses the challenge of balancing game difficulty for multiple players simultaneously, which is an incremental improvement over existing DDA approaches that focus on individual players.
The paper tackles the problem of dynamic difficulty adjustment (DDA) in games by proposing a deep learning method that optimizes user experience while considering other players and game constraints, and it empirically outperforms manual heuristics in an experiment with 200,000 players.
Dynamic difficulty adjustment ($DDA$) is a process of automatically changing a game difficulty for the optimization of user experience. It is a vital part of almost any modern game. Most existing DDA approaches concentrate on the experience of a player without looking at the rest of the players. We propose a method that automatically optimizes user experience while taking into consideration other players and macro constraints imposed by the game. The method is based on deep neural network architecture that involves a count loss constraint that has zero gradients in most of its support. We suggest a method to optimize this loss function and provide theoretical analysis for its performance. Finally, we provide empirical results of an internal experiment that was done on $200,000$ players and was found to outperform the corresponding manual heuristics crafted by game design experts.