Reinforcement Learning of Intelligent Characters in Fighting Action Games

In this paper, we investigate reinforcement learning (RL) of intelligent characters, based on neural network technology, for fighting action games. RL can be either on-policy or off-policy. We apply both schemes to tabula rasa learning and adaptation. The experimental results show that (1) in tabula...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Cho, Byeong Heon, Jung, Sung Hoon, Shim, Kwang-Hyun, Seong, Yeong Rak, Oh, Ha Ryoung
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Action Game Applied sciences Artificial intelligence Computer science control theory systems Computer systems and distributed systems. User interface Exact sciences and technology Input State Output Action Reinforcement Learn Software Static Algorithm
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!