Accession Number:

ADA516703

Title:

Developing an Effective and Efficient Real Time Strategy Agent for Use as a Computer Generated Force

Descriptive Note:

Master's thesis

Corporate Author:

AIR FORCE INST OF TECH WRIGHT-PATTERSON AFB OH GRADUATE SCHOOL OF ENGINEERING AND MANAGEMENT

Personal Author(s):

• Weissgerber, Kurt

Report Date:

2010-03-01

Pagination or Media Count:

137.0

Abstract:

Computer Generated Forces CGF are used as units or people in military training and simulation. The use of CGF significantly reduces the time and money required for effective training. Real Time Strategy RTS games place players in control of a large force whose goal is to defeat the opponent. The military setting of RTS games makes them an excellent platform for the development and testing of CGF. While significant research has been done into RTS agent development, most of the developed agents are only able to exhibit good tactical behavior. By analyzing prior games played by an opposing agent, an RTS agent could determine the opponents strengths and weaknesses and develop a strategy which neutralizes the strengths and capitalizes on the weaknesses. It could then execute this strategy in an RTS game. This research develops the Killer Bee Artificial Intelligence KBAI. KBAI takes a classifier for the RTS domain, uses it to generate an effective counter-strategy, and executes the tactics required for the strategy.

Descriptors:

• *ARTIFICIAL INTELLIGENCE
• *COMPUTER GAMES
• DECISION MAKING
• STRATEGY
• COST EFFECTIVENESS
• SPECIFICATIONS
• TIME
• CLASSIFICATION
• MILITARY TRAINING
• MILITARY TACTICS
• SIMULATION
• ALGORITHMS
• THESES

Subject Categories:

• Computer Programming and Software
• Cybernetics
• Military Forces and Organizations

Distribution Statement:

APPROVED FOR PUBLIC RELEASE