Automatic difficulty management and testing in games using a framework based on behavior trees and genetic algorithms
This addresses the challenge of providing compelling experiences for users with varying skills in video games and virtual environments, though it appears incremental as it builds on existing methods like behavior trees and genetic algorithms.
The paper tackled the problem of manually tuning game agent behaviors for adaptive difficulty by creating a framework that automatically generates diverse behaviors for different difficulty classes, and also developed automated tests to detect code defects and logic exploits with reduced human effort.
The diversity of agent behaviors is an important topic for the quality of video games and virtual environments in general. Offering the most compelling experience for users with different skills is a difficult task, and usually needs important manual human effort for tuning existing code. This can get even harder when dealing with adaptive difficulty systems. Our paper's main purpose is to create a framework that can automatically create behaviors for game agents of different difficulty classes and enough diversity. In parallel with this, a second purpose is to create more automated tests for showing defects in the source code or possible logic exploits with less human effort.