Procedurally generating rules to adapt difficulty for narrative puzzle games

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review


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.
Original languageEnglish
Title of host publicationProceedings of the IEEE Conference on Game
Number of pages4
Publication date2023
ISBN (Print)979-8-3503-2278-1
ISBN (Electronic)979-8-3503-2277-4
Publication statusPublished - 2023
SeriesProceedings of the 2023 IEEE conference on Games


Dive into the research topics of 'Procedurally generating rules to adapt difficulty for narrative puzzle games'. Together they form a unique fingerprint.

Cite this