Polygames: Improved Zero Learning

Since DeepMind's AlphaZero, Zero learning quickly became the state-of-the-art method for many board games. It can be improved using a fully convolutional structure (no fully connected layer). Using such an architecture plus global pooling, we can create bots independent of the board size. The t...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-01
Hauptverfasser:	Cazenave, Tristan, Yen-Chi, Chen, Guan-Wei, Chen, Shi-Yu, Chen, Xian-Dong Chiu, Dehos, Julien, Elsa, Maria, Gong, Qucheng, Hu, Hengyuan, Khalidov, Vasil, Cheng-Ling, Li, Lin, Hsin-I, Yu-Jin, Lin, Martinet, Xavier, Mella, Vegard, Rapin, Jeremy, Roziere, Baptiste, Synnaeve, Gabriel, Teytaud, Fabien, Teytaud, Olivier, Shi-Cheng, Ye, Yi-Jun, Ye, Shi-Jim Yen, Zagoruyko, Sergey
Format:	Artikel
Sprache:	eng
Schlagworte:	Boards of directors Games Learning Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!