Deep Learning for Procedural Content Generation

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.

This is a pre-print of an article published in Neural Computing and Applications. The final authenticated version is available online at: https://doi.org/10.1007/s00521-020-05383-8

References in corpus (22)

• Deep Learning in Neural Networks: An Overview
• Auto-Encoding Variational Bayes
• LSTM: A Search Space Odyssey
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• A Neural Representation of Sketch Drawings
• Deep Learning for Procedural Content Generation
• Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
• Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space
• Friend, Collaborator, Student, Manager: How Design of an AI-Driven Game Level Editor Affects Creators
• Jukebox: A Generative Model for Music
• Super Mario as a String: Platformer Level Generation Via LSTMs
• Transforming Exploratory Creativity with DeLeNoX
• Tile Pattern KL-Divergence for Analysing and Evolving Game Levels
• CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-scale Pattern Generation
• Controllable Level Blending between Games using Variational Autoencoders
• Efficient Generation of Structured Objects with Constrained Adversarial Networks
• Pairing Character Classes in a Deathmatch Shooter Game via a Deep-Learning Surrogate Model
• Using Fractal Neural Networks to Play SimCity 1 and Conway's Game of Life at Variable Scales
• Dance Dance Convolution
• Exploring Level Blending across Platformers via Paths and Affordances
• Game Level Clustering and Generation using Gaussian Mixture VAEs
• Adaptive Procedural Task Generation for Hard-Exploration Problems

Cited by in corpus (19)

• Deep Learning for Procedural Content Generation
• Level Generation Through Large Language Models
• Copyright in Generative Deep Learning
• The Metaverse: Survey, Trends, Novel Pipeline Ecosystem & Future Directions
• Creativity and Machine Learning: A Survey
• Real Risks of Fake Data: Synthetic Data, Diversity-Washing and Consent Circumvention
• TreeSketchNet: From Sketch To 3D Tree Parameters Generation
• SuSketch: Surrogate Models of Gameplay as a Design Assistant
• Reinforcement Learning with Dual-Observation for General Video Game Playing
• Balancing of competitive two-player Game Levels with Reinforcement Learning
• Simulation-Driven Balancing of Competitive Game Levels with Reinforcement Learning
• Intelligent Generation of Graphical Game Assets: A Conceptual Framework and Systematic Review of the State of the Art
• G-PCGRL: Procedural Graph Data Generation via Reinforcement Learning
• Improving Conditional Level Generation using Automated Validation in Match-3 Games
• Level generation and style enhancement -- deep learning for game development overview
• Democratizing Game Modding with GenAI: A Case Study of StarCharM, a Stardew Valley Character Maker
• Learning Controllable Content Generators
• Active Reinforcement Learning over MDPs
• Compressing and Comparing the Generative Spaces of Procedural Content Generators