Published on Tue Jan 14 2020

Generative Adversarial Network Rooms in Generative Graph Grammar Dungeons for The Legend of Zelda

Jake Gutierrez, Jacob Schrum

Generative Adversarial Networks (GANs) have demonstrated their ability to learn patterns in data. This paper combines a GAN approach to generating individual rooms with a graph grammar approach. The GAN captures design principles of individual rooms, but the graph grammar organizes rooms into a global layout.

0
0
0
Abstract

Generative Adversarial Networks (GANs) have demonstrated their ability to learn patterns in data and produce new exemplars similar to, but different from, their training set in several domains, including video games. However, GANs have a fixed output size, so creating levels of arbitrary size for a dungeon crawling game is difficult. GANs also have trouble encoding semantic requirements that make levels interesting and playable. This paper combines a GAN approach to generating individual rooms with a graph grammar approach to combining rooms into a dungeon. The GAN captures design principles of individual rooms, but the graph grammar organizes rooms into a global layout with a sequence of obstacles determined by a designer. Room data from The Legend of Zelda is used to train the GAN. This approach is validated by a user study, showing that GAN dungeons are as enjoyable to play as a level from the original game, and levels generated with a graph grammar alone. However, GAN dungeons have rooms considered more complex, and plain graph grammar's dungeons are considered least complex and challenging. Only the GAN approach creates an extensive supply of both layouts and rooms, where rooms span across the spectrum of those seen in the training set to new creations merging design principles from multiple rooms.

Tue Mar 31 2020
Neural Networks
Interactive Evolution and Exploration Within Latent Level-Design Space of Generative Adversarial Networks
Generative Adversarial Networks (GANs) are an emerging form of indirect encoding. The GAN is trained to induce a latent space on training data. A real-valued evolutionary algorithm can search that latent space.
0
0
0
Wed Feb 12 2020
Artificial Intelligence
Fully Differentiable Procedural Content Generation through Generative Playing Networks
Generative Playing Networks is a framework that learns agent policies and generates environments in tandem. Policies are learned using an actor-critic reinforcement learning algorithm. Environments are created by a generator network which tries to provide an appropriate level of challenge for the agent.
1
0
6
Tue Jun 11 2019
Artificial Intelligence
Two-step Constructive Approaches for Dungeon Generation
This paper presents a two-step generative approach for creating dungeons in MiniDungeons 2. Generation is split into two steps, producing the architectural layout of the level as its walls and floor tiles, and then furnishing it with game objects representing the player's start and goal position.
0
0
0
Fri Apr 03 2020
Neural Networks
CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-scale Pattern Generation
Generative Adversarial Networks (GANs) are proving to be a powerful indirectgenotype-to-phenotype mapping for evolutionary search. GAN output does not scale to arbitrary dimensions, and there is no obvious way of combining multiple GAN outputs into a cohesive whole.
0
0
0
Tue May 26 2020
Artificial Intelligence
Capturing Local and Global Patterns in Procedural Content Generation via Machine Learning
Recent procedural content generation via machine learning (PCGML) methods allow learning from existing content to produce similar content automatically. While these approaches are able to generate content for different games, it is an open questions how well these approaches can capture large-scale visual patterns such as symmetry.
0
0
0
Sat Jan 30 2021
Neural Networks
Using Multiple Generative Adversarial Networks to Build Better-Connected Levels for Mega Man
Generative Adversarial Networks (GANs) can generate levels for a variety of games. This paper focuses on combining GAN-generated segments in a snaking pattern to create levels for Mega Man. Adjacent segments in such levels can be orthogonally adjacent in any direction.
0
0
0