Procedurally generating rules to adapt difficulty for narrative puzzle games
This work addresses adaptive difficulty in educational games for young children, though it appears incremental as it combines existing methods like genetic algorithms and large language models.
The paper tackled the problem of procedurally generating rules to adjust difficulty in narrative puzzle games for educational purposes, achieving an average of within two dozen generations to approximate target difficulty levels.
This paper focuses on procedurally generating rules and communicating them to players to adjust the difficulty. This is part of a larger project to collect and adapt games in educational games for young children using a digital puzzle game designed for kindergarten. A genetic algorithm is used together with a difficulty measure to find a target number of solution sets and a large language model is used to communicate the rules in a narrative context. During testing the approach was able to find rules that approximate any given target difficulty within two dozen generations on average. The approach was combined with a large language model to create a narrative puzzle game where players have to host a dinner for animals that can't get along. Future experiments will try to improve evaluation, specialize the language model on children's literature, and collect multi-modal data from players to guide adaptation.