Effective and Diverse Adaptive Game AI

Adaptive techniques tend to converge to a single optimum. For adaptive game AI, such convergence is often undesirable, as repetitive game AI is considered to be uninteresting for players. In this paper, we propose a method for automatically learning diverse but effective macros that can be used as c...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on computational intelligence and AI in games. 2009-03, Vol.1 (1), p.16-27
Hauptverfasser:	Szita, I., Ponsen, M., Spronck, P.
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptive control Adaptive control systems Artificial intelligence Computational intelligence Computational modeling Computer simulation Convergence cross-entropy method (CEM) dynamic scripting game Games Humans Learning Optimization Optimization methods Programmable control reinforcement learning Scripts Testing
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!