@inproceedings{1a158d41175f41ffa1b908edad2f7bcd,
title = "Procedurally generating rules to adapt difficulty for narrative puzzle games",
abstract = "This short 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 kindergartens. 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.",
keywords = "procedural generation, difficulty adjustment, genetic algorithm, educational games, large language models, procedural generation, difficulty adjustment, genetic algorithm, educational games, large language models",
author = "Thomas Volden and Djordje Grbic and Paolo Burelli",
year = "2023",
doi = "10.48550/arXiv.2307.05518",
language = "English",
isbn = "979-8-3503-2278-1",
series = "Proceedings of the 2023 IEEE conference on Games",
publisher = "IEEE",
pages = "1--4",
booktitle = "Proceedings of the IEEE Conference on Game",
address = "United States",
}