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.
Beschreibung
DeepChess: End-to-End Deep Neural Network for Automatic Learning in Chess
%0 Generic
%1 david2017deepchess
%A David, Eli
%A Netanyahu, Nathan S.
%A Wolf, Lior
%D 2017
%K chess dl
%R 10.1007/978-3-319-44781-0_11
%T DeepChess: End-to-End Deep Neural Network for Automatic Learning in
Chess
%U http://arxiv.org/abs/1711.09667
%X 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.
@misc{david2017deepchess,
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.},
added-at = {2019-08-17T21:54:54.000+0200},
author = {David, Eli and Netanyahu, Nathan S. and Wolf, Lior},
biburl = {https://www.bibsonomy.org/bibtex/237280887ae70bd15ec2a91e9dca56614/bechr7},
description = {DeepChess: End-to-End Deep Neural Network for Automatic Learning in Chess},
doi = {10.1007/978-3-319-44781-0_11},
interhash = {447129783dec74890a514767383b4d74},
intrahash = {37280887ae70bd15ec2a91e9dca56614},
keywords = {chess dl},
note = {cite arxiv:1711.09667Comment: Winner of Best Paper Award in ICANN 2016},
timestamp = {2019-08-17T21:54:54.000+0200},
title = {DeepChess: End-to-End Deep Neural Network for Automatic Learning in
Chess},
url = {http://arxiv.org/abs/1711.09667},
year = 2017
}