A Demonstration of Pathfinding-Based Puzzle Generation with Adaptive Difficulty

Abstract

In this demonstration paper, we showcase an adaptive puzzle-generation game designed to dynamically adjust puzzle difficulty in real-time for individual users. The game utilizes a genetic algorithm to procedurally generate pathfinding-based puzzles tailored specifically to each player's skill level and interaction patterns. A player-modeling mechanism continuously monitors user behaviors and interactions, enabling the game to match puzzle complexity to each player's abilities. By adaptively calibrating challenge levels, this system seeks to enhance player engagement, reduce frustration, and maintain an optimal difficulty balance.