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, 2020, 3
doi: 10.25534/tuprints-00013370
Artikel, Zweitveröffentlichung

Kurzbeschreibung (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.

Typ des Eintrags: Artikel
Erschienen: 2020
Autor(en): Czech, Johannes ; Willig, Moritz ; Beyer, Alena ; Kersting, Kristian ; Fürnkranz, Johannes
Art des Eintrags: Zweitveröffentlichung
Titel: Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data
Sprache: Englisch
Publikationsjahr: 2020
Publikationsdatum der Erstveröffentlichung: 2020
Verlag: Frontiers
Titel der Zeitschrift, Zeitung oder Schriftenreihe: Frontiers in Artificial Intelligence
Jahrgang/Volume einer Zeitschrift: 3
DOI: 10.25534/tuprints-00013370
URL / URN: https://doi.org/10.3389/frai.2020.00024
Herkunft: Zweitveröffentlichung aus gefördertem Golden Open Access
Kurzbeschreibung (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.

URN: urn:nbn:de:tuda-tuprints-133708
Sachgruppe der Dewey Dezimalklassifikatin (DDC): 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Knowledge Engineering
Hinterlegungsdatum: 25 Aug 2020 13:20
Letzte Änderung: 02 Sep 2020 11:06
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen