Evolutionary Artificial Neural Network Weight Tuning to Optimize Decision Making for an Abstract Game

Abstract

Abstract strategy games present a deterministic perfect information environment with which to test the strategic capabilities of artificial intelligence systems. With no unknowns or random elements, only the competitors' performances impact the results. This thesis takes one such game, Lines of Action, and attempts to develop a competitive heuristic. Due to the complexity of Lines of Action, artificial neural networks are utilized to model the relative values of board states. An application, pLoGANN (Parallel Lines of Action with Genetic Algorithm and Neural Networks), is developed to train the weights of this neural network by implementing a genetic algorithm over a distributed environment. While pLoGANN proved to be designed efficiently, it failed to produce a competitive Lines of Action player, shedding light on the difficulty of developing a neural network to model such a large and complex solution space.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2010
Accession Number
ADA516710

Entities

People

  • Corey M. Miller

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies
  • Human Systems

DTIC Thesaurus Topics

  • Air Force
  • Algorithms
  • Artificial Intelligence
  • Cells
  • Computer Networks
  • Computer Science
  • Computers
  • Engineering
  • Mesh Networks
  • Network Topology
  • Networks
  • Operating Systems
  • Probability
  • Reinforcement Learning
  • Standards
  • Stochastic Processes
  • United States

Readers

  • Game Theory.
  • Neural Network Machine Learning.
  • Software Engineering

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks
  • Biotechnology
  • Space