Creating Pro-Level AI for a Real-Time Fighting Game Using Deep Reinforcement Learning

Reinforcement learning combined with deep neural networks has performed remarkably well in many genres of games recently. It has surpassed human-level performance in fixed game environments and turn-based two player board games. However, to the best of our knowledge, current research has yet to prod...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-01
Hauptverfasser:	Oh, Inseok, Rho, Seungeun, Moon, Sangbin, Son, Seongho, Lee, Hyoil, Chung, Jinyun
Format:	Artikel
Sprache:	eng
Schlagworte:	Curricula Games Human performance Machine learning Neural networks Real time
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!