Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network
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 one in the original corpus, but is further improved by application of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Specifically, various fitness functions are used to discover levels within the latent space of the GAN that maximize desired properties. Simple static properties are optimized, such as a given distribution of tile types. Additionally, the champion A* agent from the 2009 Mario AI competition is used to assess whether a level is playable, and how many jumping actions are required to beat it. These fitness functions allow for the discovery of levels that exist within the space of examples designed by experts, and also guide the search towards levels that fulfill one or more specified objectives.
Code (3)
Tasks
Generative Adversarial NetworkSNES GamesMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometry
Deep generative models can automatically create content of diverse types. However, there are no guarantees that such content will satisfy the criteria necessary to present it to end-users and be functional, e.g. the gene…
Illuminating Mario Scenes in the Latent Space of a Generative Adversarial Network
Generative adversarial networks (GANs) are quickly becoming a ubiquitous approach to procedurally generating video game levels. While GAN generated levels are stylistically similar to human-authored examples, human desig…
DiversityGenerative Adversarial NetworkImproving Deep Localized Level Analysis: How Game Logs Can Help
Player modelling is the field of study associated with understanding players. One pursuit in this field is affect prediction: the ability to predict how a game will make a player feel. We present novel improvements to af…
Hybrid Encoding For Generating Large Scale Game Level Patterns With Local Variations
Generative Adversarial Networks (GANs) are a powerful indirect genotype-to-phenotype mapping for evolutionary search. Much previous work applying GANs to level generation focuses on fixed-size segments combined into a wh…
Super Mario as a String: Platformer Level Generation Via LSTMs
The procedural generation of video game levels has existed for at least 30 years, but only recently have machine learning approaches been used to generate levels without specifying the rules for generation. A number of t…