Using Skill Rating as Fitness on the Evolution of GANs

04/09/2020
by   Victor Costa, et al.
1

Generative Adversarial Networks (GANs) are an adversarial model that achieved impressive results on generative tasks. In spite of the relevant results, GANs present some challenges regarding stability, making the training usually a hit-and-miss process. To overcome these challenges, several improvements were proposed to better handle the internal characteristics of the model, such as alternative loss functions or architectural changes on the neural networks used by the generator and the discriminator. Recent works proposed the use of evolutionary algorithms on GAN training, aiming to solve these challenges and to provide an automatic way to find good models. In this context, COEGAN proposes the use of coevolution and neuroevolution to orchestrate the training of GANs. However, previous experiments detected that some of the fitness functions used to guide the evolution are not ideal. In this work we propose the evaluation of a game-based fitness function to be used within the COEGAN method. Skill rating is a metric to quantify the skill of players in a game and has already been used to evaluate GANs. We extend this idea using the skill rating in an evolutionary algorithm to train GANs. The results show that skill rating can be used as fitness to guide the evolution in COEGAN without the dependence of an external evaluator.

READ FULL TEXT
research
07/13/2020

Exploring the Evolution of GANs through Quality Diversity

Generative adversarial networks (GANs) achieved relevant advances in the...
research
08/14/2018

Skill Rating for Generative Models

We explore a new way to evaluate generative models using insights from e...
research
01/31/2021

Demonstrating the Evolution of GANs through t-SNE

Generative Adversarial Networks (GANs) are powerful generative models th...
research
10/11/2019

Evolutionary Multi-Objective Optimization Driven by Generative Adversarial Networks (GANs)

Recently, more and more works have proposed to drive evolutionary algori...
research
12/30/2017

Towards co-evolution of fitness predictors and Deep Neural Networks

Deep neural networks proved to be a very useful and powerful tool with m...
research
08/04/2023

A State-Space Perspective on Modelling and Inference for Online Skill Rating

This paper offers a comprehensive review of the main methodologies used ...
research
05/22/2020

Host-Pathongen Co-evolution Inspired Algorithm Enables Robust GAN Training

Generative adversarial networks (GANs) are pairs of artificial neural ne...

Please sign up or login with your details

Forgot password? Click here to reset