Cargando…
Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data
Deep neural networks have been successfully applied in learning the board games Go, chess, and shogi without prior knowledge by making use of reinforcement learning. Although starting from zero knowledge has been shown to yield impressive results, it is associated with high computationally costs esp...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7861260/ https://www.ncbi.nlm.nih.gov/pubmed/33733143 http://dx.doi.org/10.3389/frai.2020.00024 |
_version_ | 1783647047376699392 |
---|---|
author | Czech, Johannes Willig, Moritz Beyer, Alena Kersting, Kristian Fürnkranz, Johannes |
author_facet | Czech, Johannes Willig, Moritz Beyer, Alena Kersting, Kristian Fürnkranz, Johannes |
author_sort | Czech, Johannes |
collection | PubMed |
description | Deep neural networks have been successfully applied in learning the board games Go, chess, and shogi without prior knowledge by making use of reinforcement learning. Although starting from zero knowledge has been shown to yield impressive results, it is associated with high computationally costs especially for complex games. With this paper, we present CrazyAra which is a neural network based engine solely trained in supervised manner for the chess variant crazyhouse. Crazyhouse is a game with a higher branching factor than chess and there is only limited data of lower quality available compared to AlphaGo. Therefore, we focus on improving efficiency in multiple aspects while relying on low computational resources. These improvements include modifications in the neural network design and training configuration, the introduction of a data normalization step and a more sample efficient Monte-Carlo tree search which has a lower chance to blunder. After training on 569537 human games for 1.5 days we achieve a move prediction accuracy of 60.4%. During development, versions of CrazyAra played professional human players. Most notably, CrazyAra achieved a four to one win over 2017 crazyhouse world champion Justin Tan (aka LM Jann Lee) who is more than 400 Elo higher rated compared to the average player in our training set. Furthermore, we test the playing strength of CrazyAra on CPU against all participants of the second Crazyhouse Computer Championships 2017, winning against twelve of the thirteen participants. Finally, for CrazyAraFish we continue training our model on generated engine games. In 10 long-time control matches playing Stockfish 10, CrazyAraFish wins three games and draws one out of 10 matches. |
format | Online Article Text |
id | pubmed-7861260 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-78612602021-03-16 Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data Czech, Johannes Willig, Moritz Beyer, Alena Kersting, Kristian Fürnkranz, Johannes Front Artif Intell Artificial Intelligence Deep neural networks have been successfully applied in learning the board games Go, chess, and shogi without prior knowledge by making use of reinforcement learning. Although starting from zero knowledge has been shown to yield impressive results, it is associated with high computationally costs especially for complex games. With this paper, we present CrazyAra which is a neural network based engine solely trained in supervised manner for the chess variant crazyhouse. Crazyhouse is a game with a higher branching factor than chess and there is only limited data of lower quality available compared to AlphaGo. Therefore, we focus on improving efficiency in multiple aspects while relying on low computational resources. These improvements include modifications in the neural network design and training configuration, the introduction of a data normalization step and a more sample efficient Monte-Carlo tree search which has a lower chance to blunder. After training on 569537 human games for 1.5 days we achieve a move prediction accuracy of 60.4%. During development, versions of CrazyAra played professional human players. Most notably, CrazyAra achieved a four to one win over 2017 crazyhouse world champion Justin Tan (aka LM Jann Lee) who is more than 400 Elo higher rated compared to the average player in our training set. Furthermore, we test the playing strength of CrazyAra on CPU against all participants of the second Crazyhouse Computer Championships 2017, winning against twelve of the thirteen participants. Finally, for CrazyAraFish we continue training our model on generated engine games. In 10 long-time control matches playing Stockfish 10, CrazyAraFish wins three games and draws one out of 10 matches. Frontiers Media S.A. 2020-04-28 /pmc/articles/PMC7861260/ /pubmed/33733143 http://dx.doi.org/10.3389/frai.2020.00024 Text en Copyright © 2020 Czech, Willig, Beyer, Kersting and Fürnkranz. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Artificial Intelligence Czech, Johannes Willig, Moritz Beyer, Alena Kersting, Kristian Fürnkranz, Johannes Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data |
title | Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data |
title_full | Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data |
title_fullStr | Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data |
title_full_unstemmed | Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data |
title_short | Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data |
title_sort | learning to play the chess variant crazyhouse above world champion level with deep neural networks and human data |
topic | Artificial Intelligence |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7861260/ https://www.ncbi.nlm.nih.gov/pubmed/33733143 http://dx.doi.org/10.3389/frai.2020.00024 |
work_keys_str_mv | AT czechjohannes learningtoplaythechessvariantcrazyhouseaboveworldchampionlevelwithdeepneuralnetworksandhumandata AT willigmoritz learningtoplaythechessvariantcrazyhouseaboveworldchampionlevelwithdeepneuralnetworksandhumandata AT beyeralena learningtoplaythechessvariantcrazyhouseaboveworldchampionlevelwithdeepneuralnetworksandhumandata AT kerstingkristian learningtoplaythechessvariantcrazyhouseaboveworldchampionlevelwithdeepneuralnetworksandhumandata AT furnkranzjohannes learningtoplaythechessvariantcrazyhouseaboveworldchampionlevelwithdeepneuralnetworksandhumandata |