Tactical AI in Real Time Strategy Games

Abstract

The real time strategy (RTS) tactical decision making problem is a difficult problem. It is generally more complex due to its high degree of time sensitivity. This research effort presents a novel approach to this problem within an educational, teaching objective. Particular decision focus is target selection for a artificial intelligence (AI) RTS game model. The use of multi-objective evolutionary algorithms (MOEAs) in this tactical decision making problem allows an AI agent to make fast, effective solutions that do not require modification to the current environment. This approach allows for the creation of a generic solution building tool that is capable of performing well against scripted opponents without requiring expert training or deep tree searches. The experimental results validate that MOEAs can control an on-line agent capable of out performing a variety AI RTS opponent test scripts.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 26, 2015
Accession Number
ADA615240

Entities

People

  • Donald A. Gruber

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies
  • Human Systems

DTIC Thesaurus Topics

  • Air Force
  • Air Power
  • Algorithms
  • Artificial Intelligence
  • Combat Simulations
  • Computational Science
  • Computers
  • Evolutionary Algorithms
  • Experimental Design
  • Genetic Algorithms
  • Governments
  • Particle Swarm Optimization
  • Statistical Analysis
  • Students
  • United States Government
  • War Games
  • Warfare

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Game Theory.
  • Geospatial Intelligence and Artificial Intelligence Analytics

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms