Proceedings of the Genetic and Evolutionary Computation Conference 2018
DOI: 10.1145/3205455.3205517
|View full text |Cite
|
Sign up to set email alerts
|

Evolving mario levels in the latent space of a deep convolutional generative adversarial network

Abstract: Generative Adversarial Networks (GANs) are a machine learning approach capable of generating novel example outputs across a space of provided training examples. Procedural Content Generation (PCG) of levels for video games could benefit from such models, especially for games where there is a pre-existing corpus of levels to emulate. This paper trains a GAN to generate levels for Super Mario Bros using a level from the Video Game Level Corpus. The approach successfully generates a variety of levels similar to o… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
259
0

Year Published

2019
2019
2022
2022

Publication Types

Select...
4
3
3

Relationship

3
7

Authors

Journals

citations
Cited by 216 publications
(259 citation statements)
references
References 23 publications
0
259
0
Order By: Relevance
“…Super Mario Bros and The Legend of Zelda). It has been used for PCG research using autoencoders [9], generative adversarial networks (GANs) [10], long short-term memories (LSTMs) [11], multidimensional Markov chains [12, Sec. 3.3.1], and automated game design learning [13].…”
Section: Summerville Et Al Define Procedural Content Generation Via mentioning
confidence: 99%
“…Super Mario Bros and The Legend of Zelda). It has been used for PCG research using autoencoders [9], generative adversarial networks (GANs) [10], long short-term memories (LSTMs) [11], multidimensional Markov chains [12, Sec. 3.3.1], and automated game design learning [13].…”
Section: Summerville Et Al Define Procedural Content Generation Via mentioning
confidence: 99%
“…One use of DL for game playing in the game production process is for game testing, where artificial agents test that levels are solvable or that the difficulty is appropriate. DL might see its most prominent use in the games industry not for playing games, but for generating game content [130] based on training on existing content [140], [158], or for modeling player experience [169].…”
Section: ) Dealing With Extremely Large Decision Spacesmentioning
confidence: 99%
“…We predict that in the near future, generative modelling techniques from machine learning, such as Generative and Adversarial Networks (GANs) [24], will allow users to personalise their avatars to an unprecedented level or allow the creation of an unlimited variety of realistic textures and assets in games. This idea of Procedural Content Generation via Machine Learning (PCGML) [81], is a new emerging research area that has already led to promising results in generating levels for games such as Doom [23] or Super Mario [87].…”
Section: Journals Conferences and Competitionsmentioning
confidence: 99%