DeepChess: End-to-End Deep Neural Network for Automatic Learning in Chess

TL;DR

This paper introduces DeepChess, an end-to-end deep neural network that learns to evaluate chess positions and select favorable moves without prior domain knowledge, achieving grandmaster-level performance solely from game data.

Contribution

It presents the first end-to-end deep learning approach for chess that does not rely on handcrafted features or domain-specific knowledge, matching top chess programs.

Findings

DeepChess performs at a grandmaster level.

The model learns from millions of game datasets.

It rivals state-of-the-art chess engines.

Abstract

We present an end-to-end learning method for chess, relying on deep neural networks. Without any a priori knowledge, in particular without any knowledge regarding the rules of chess, a deep neural network is trained using a combination of unsupervised pretraining and supervised training. The unsupervised training extracts high level features from a given position, and the supervised training learns to compare two chess positions and select the more favorable one. The training relies entirely on datasets of several million chess games, and no further domain specific knowledge is incorporated. The experiments show that the resulting neural network (referred to as DeepChess) is on a par with state-of-the-art chess playing programs, which have been developed through many years of manual feature selection and tuning. DeepChess is the first end-to-end machine learning-based method that results in a grandmaster-level chess playing performance.