Research

A Game Platform for Intelligent Agents

Chris Brown, George Ferguson, Peter Barnum, Bo Hu, and David Costello

The Quagents system provides a flexible interface to the functionality of a game engine. The goal is to make interactive games a useful research and teaching vehicle for academics. Quagents is freely available, and runs under Unix/Linux, Windows, and Mac OS X. Intelligent agent controllers may be programmed in any language that supports sockets. A communications protocol between the controller and the bot resembles that between the high-level software and low-level controller of a mobile robot. More complex APIs may be built on the protocol that support complex interactions like trading. We describe the Quagent architecture and research and teaching applications.

 

The official Quagent webpage is at http://www.cs.rochester.edu/research/quagents/ .

Publications

"Robust Agent Teams"
P.C. Barnum
Undergraduate Honors Thesis, 2005
[PDF]

"Quagents: A Game Platform for Intelligent Agents"
C.M. Brown, G. Ferguson, P.C. Barnum, B. Hu, and D. Costello
AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 2005
[PDF]

"Quake II as a Robotic and Multi-Agent Platform"
C.M. Brown, P.C. Barnum, D. Costello, G. Ferguson, B. Hu, and M. Van Wie
Technical Report 853, University of Rochester Computer Science Department, 2004
[PDF]