Chess2vec: Learning Vector Representations for Chess
Machine Learning
2020-11-03 v1 Artificial Intelligence
Abstract
We conduct the first study of its kind to generate and evaluate vector representations for chess pieces. In particular, we uncover the latent structure of chess pieces and moves, as well as predict chess moves from chess positions. We share preliminary results which anticipate our ongoing work on a neural network architecture that learns these embeddings directly from supervised feedback.
Cite
@article{arxiv.2011.01014,
title = {Chess2vec: Learning Vector Representations for Chess},
author = {Berk Kapicioglu and Ramiz Iqbal and Tarik Koc and Louis Nicolas Andre and Katharina Sophia Volz},
journal= {arXiv preprint arXiv:2011.01014},
year = {2020}
}
Comments
Relational Representation Learning Workshop, NeurIPS 2018