TY - GEN
T1 - Search-Based Exploration and Diagnosis of TOAD-GAN
AU - Edwards, Maria
AU - Jiang, Ming
AU - Togelius, Julian
N1 - Publisher Copyright:
Copyright © 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2021
Y1 - 2021
N2 - Generative Adversarial Networks (GANs) have been used with great success to generate images. They have also been applied to the task of Procedural Content Generation (PCG) in games, particularly for level generation, with various approaches taken to solving the problem of training data. One of those approaches, TOAD-GAN (Token-Based One-Shot Arbitrary Dimension Generative Adversarial Network) (Awiszus, Schubert, and Rosenhahn 2020), can generate levels based on a single training example and has been able to closely reproduce token patterns found in the training sample. While TOAD-GAN is an impressive achievement, questions remain about what exactly it has learned. Can the generator be made to produce levels that are substantially different from the level it has been trained on? Can it reproduce specific level segments? How different are the generated levels? We investigate these questions and others by using the CMA-ES algorithm for Latent Space Evolution. To make the search space feasible, we use a random projection in latent space. We propose the investigation undertaken here as a paradigm for studies into what machine-learned generators have actually learned, and also as a test of a new method for projecting from a smaller search space to a larger latent space.
AB - Generative Adversarial Networks (GANs) have been used with great success to generate images. They have also been applied to the task of Procedural Content Generation (PCG) in games, particularly for level generation, with various approaches taken to solving the problem of training data. One of those approaches, TOAD-GAN (Token-Based One-Shot Arbitrary Dimension Generative Adversarial Network) (Awiszus, Schubert, and Rosenhahn 2020), can generate levels based on a single training example and has been able to closely reproduce token patterns found in the training sample. While TOAD-GAN is an impressive achievement, questions remain about what exactly it has learned. Can the generator be made to produce levels that are substantially different from the level it has been trained on? Can it reproduce specific level segments? How different are the generated levels? We investigate these questions and others by using the CMA-ES algorithm for Latent Space Evolution. To make the search space feasible, we use a random projection in latent space. We propose the investigation undertaken here as a paradigm for studies into what machine-learned generators have actually learned, and also as a test of a new method for projecting from a smaller search space to a larger latent space.
UR - http://www.scopus.com/inward/record.url?scp=85129782847&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85129782847&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85129782847
T3 - 17th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2021
SP - 140
EP - 147
BT - 17th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2021
PB - Association for the Advancement of Artificial Intelligence
T2 - 17th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2021
Y2 - 11 October 2021 through 15 October 2021
ER -