Style Transfer Generative Adversarial Networks: Learning to Play Chess Differently

2017/02/22 by M. Chidambaram, Muthuraman Chidambaram, Yanjun Qi +2 · 1 citation
Computer Science · Economics, Econometrics and Finance · Physics and Astronomy · #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Model Reduction and Neural Networks #Sports Analytics and Performance #cs.LG

paper · pdf · doi:10.48550/arxiv.1702.06762

style transfer, Generative Adversarial Networks

openalex publication_date 2017/02/22 · openalex created_date 2017/03/03 · arxiv created 2017/05/07 · arxiv updated 2017/05/09 · openalex updated_date 2026/07/28

Abstract

The idea of style transfer has largely only been explored in image-based tasks, which we attribute in part to the specific nature of loss functions used for style transfer. We propose a general formulation of style transfer as an extension of generative adversarial networks, by using a discriminator to regularize a generator with an otherwise separate loss function. We apply our approach to the task of learning to play chess in the style of a specific player, and present empirical evidence for the viability of our approach.

Cited by

• MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets

Related

• A Style-Based Generator Architecture for Generative Adversarial Networks
• A Style-Based Generator Architecture for Generative Adversarial Networks
• Exploring the Neural Algorithm of Artistic Style
• Style is a Distribution of Features
• Learning from Multi-domain Artistic Images for Arbitrary Style Transfer