Controlling non-player characters using support vector machines

Authors:
Pedro Melendez
Affiliations:
Algoma University, Ontario, Canada
Venue:
Future Play '09 Proceedings of the 2009 Conference on Future Play on @ GDC Canada
Year:
2009

Citing 5
Cited 0

An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Artificial Intelligence: A Modern Approach

Artificial Intelligence: A Modern Approach
AI Application Programming

AI Application Programming
Ai Game Engine Programming (Game Development Series)

Ai Game Engine Programming (Game Development Series)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Developing believable behaviours for non-player characters is an ongoing problem in the video game industry. A method to use support vector machines to control non-player characters is proposed as an alternative to classic techniques like finite state machines (FSMs). Also, the method proposed is designed to be used to achieve continuous learning even after the game is released.