TU Darmstadt / ULB / TUbiblio

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 (2020):
Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data.
In: Frontiers in Artificial Intelligence, 3, Frontiers, ISSN 2624-8212,
DOI: 10.25534/tuprints-00013370,
[Article]

Abstract

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.

Item Type: Article
Erschienen: 2020
Creators: Czech, Johannes ; Willig, Moritz ; Beyer, Alena ; Kersting, Kristian ; Fürnkranz, Johannes
Origin: Secondary publication via sponsored Golden Open Access
Title: Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data
Language: English
Abstract:

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.

Journal or Publication Title: Frontiers in Artificial Intelligence
Journal volume: 3
Publisher: Frontiers
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Knowl­edge En­gi­neer­ing
Date Deposited: 25 Aug 2020 13:20
DOI: 10.25534/tuprints-00013370
Official URL: https://doi.org/10.3389/frai.2020.00024
URN: urn:nbn:de:tuda-tuprints-133708
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details