Please use this identifier to cite or link to this item: https://www.um.edu.mt/library/oar/handle/123456789/81990
Title: Automatic puzzle level generation : a general approach using a description language
Authors: Khalifa, Ahmed
Fayek, Magda
Keywords: Video games -- Design
Level design (Computer science)
Artificial intelligence
Machine learning
Issue Date: 2015
Publisher: Institute of Electrical and Electronics Engineers
Citation: Khalifa, A., & Fayek, M. (2015). Automatic puzzle level generation : a general approach using a description language. Sixth International Conference on Computational Creativity, ICCC 2015, Park City.
Abstract: In this paper, we present a general technique to generate and evaluate puzzle levels made by Puzzle Script. Puzzle Script is a videogame description language created by Stephen Lavelle for scripting puzzle games. We propose a system to help in generating levels for Puzzle Script without any restriction on the current game rules. Two different approaches are used with a trade off between speed (Constructive approach) and playability (Genetic approach). These two approaches use a level evaluator that calculates the scores of the generated levels based on their playability and challenge. The generated levels are assessed by human players statistically, and the results show that the constructive approach is capable of generating playable levels up to 90%, while genetic approach can reach up to 100%. The results also show a high correlation between the system scores and the human scores.
URI: https://www.um.edu.mt/library/oar/handle/123456789/81990
Appears in Collections:Scholarly Works - InsDG

Files in This Item:
File Description SizeFormat 
Automatic_puzzle_level_generation_a_general_approach_using_a_description_language_2015.pdf476.25 kBAdobe PDFView/Open


Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.