Deep Static and Dynamic Level Analysis: A Study on Infinite Mario
Full Text: 14068-61962-1-PB.pdf
Automatic analysis of game levels can provide as- sistance to game designers and procedural content generation. We introduce a static-dynamic scale to categorize level analysis strategies, which captures the extent that the analysis depends on player simulation. Due to its ability to automatically learn intermediate representations for the task, a convolutional neural network (CNN) provides a general tool for both types of analysis. In this paper, we explore the use of CNN to analyze 1,437 Infinite Mario levels. We further propose a deep reinforcement learning technique for dynamic analysis, which allows the simulated player to pay a penalty to reduce error in its control. We empirically demonstrate the effectiveness of our techniques and complementarity of dynamic and static analysis.
Citation
M. Guzdial, N. Sturtevant, B. Li. "Deep Static and Dynamic Level Analysis: A Study on Infinite Mario". Artificial Intelligence and Interactive Entertainment Conference (AIIDE), pp 31-38, October 2016.| Keywords: | games, neural nets, automatic analysis |
| Category: | In Conference |
| Web Links: | AAAI |
BibTeX
@incollection{Guzdial+al:AIIDE16,
author = {Matthew Guzdial and Nathan R. Sturtevant and Boyang Li},
title = {Deep Static and Dynamic Level Analysis: A Study on Infinite Mario},
Pages = {31-38},
booktitle = {Artificial Intelligence and Interactive Entertainment Conference
(AIIDE)},
year = 2016,
}Last Updated: July 06, 2020Submitted by Sabina P
