Conference proceeding
Understanding Mario: An Evaluation of Design Metrics For Platformers
PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON THE FOUNDATIONS OF DIGITAL GAMES (FDG'17), v 130151
01 Jan 2017
Abstract
Evaluating the output of content generators is still one of the key open research challenges in Procedural Content Generation (PCG). This paper presents a collection of metrics for evaluating the quality of platform game levels, and analyzes how well these metrics are able to capture the human-perceived difficulty, visual aesthetics and enjoyment of these levels. We show empirically, in the context of Infinite Mario Bros (IMB), that some of the proposed metrics yield correlation values with human ratings that are near empirical upper bounds derived from a human inter-rater agreement study. We also show that a simple linear regression model using a subset of our metrics as input features is able to substantially outperform a previous approach that uses a neural network for predicting human-perceived difficulty, visual aesthetics, and enjoyment in IMB levels.
Metrics
Details
- Title
- Understanding Mario: An Evaluation of Design Metrics For Platformers
- Creators
- Adam Summerville - University of California, Santa CruzJulian R. H. Marino - Universidade de São PauloSam Snodgrass - Drexel UniversitySantiago Ontanon - Drexel UniversityLevi H. S. Lelis - Universidade Federal de Viçosa
- Contributors
- A Canossa (Editor)C Harteveld (Editor)J Zhu (Editor)M Sicart (Editor)S Deterding (Editor)
- Publication Details
- PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON THE FOUNDATIONS OF DIGITAL GAMES (FDG'17), v 130151
- Conference
- 12TH INTERNATIONAL CONFERENCE ON THE FOUNDATIONS OF DIGITAL GAMES (FDG'17), 12th
- Publisher
- Assoc Computing Machinery
- Number of pages
- 10
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science
- Web of Science ID
- WOS:000426967500008
- Scopus ID
- 2-s2.0-85030784133
- Other Identifier
- 991019167774404721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Computer Science, Interdisciplinary Applications
- Computer Science, Software Engineering