Deep Learning for Procedural Content Generation

TL;DR

This paper surveys the application of deep learning techniques to procedural content generation in video games, highlighting recent advances, potential future methods, and limitations in the field.

Contribution

It provides a comprehensive overview of deep learning methods used in game content generation, including current applications, potential future approaches, and discusses limitations and future directions.

Findings

Deep learning has been successfully applied to generate various game content types.

Combining deep learning with traditional methods enhances content generation.

The paper identifies limitations and suggests future research directions in deep learning for game content.

Abstract

Procedural content generation in video games has a long history. Existing procedural content generation methods, such as search-based, solver-based, rule-based and grammar-based methods have been applied to various content types such as levels, maps, character models, and textures. A research field centered on content generation in games has existed for more than a decade. More recently, deep learning has powered a remarkable range of inventions in content production, which are applicable to games. While some cutting-edge deep learning methods are applied on their own, others are applied in combination with more traditional methods, or in an interactive setting. This article surveys the various deep learning methods that have been applied to generate game content directly or indirectly, discusses deep learning methods that could be used for content generation purposes but are rarely used today, and envisages some limitations and potential future directions of deep learning for procedural content generation.