Center for Human Modeling and Simulation

Document Type

Journal Article

Date of this Version

April 2000

Comments

Postprint version. Published in AAAI Spring Symposium, 2000.
Publisher URL: http://citeseer.ist.psu.edu/264852.html

Abstract

We introduce a prototype for building a strategy game. A player can control and modify the behavior of all the characters in a game, and introduce new strategies, through the powerful medium of natural language instructions. We describe a Parameterized Action Representation (PAR) designed to bridge the gap between natural language instructions and the virtual agents who are to carry them out. We will illustrate PAR through an interactive demonstration of a multi-agent strategy game.

Share

COinS
 

Date Posted: 18 July 2007

This document has been peer reviewed.