Playing Abstract Games with Hidden States (Spatial and Non-Spatial)

Abstract

OUTLINE: * Our domain of research * The mathematics of strategically complex game playing - Move evaluation - Min/max depth search - temporal difference learning. * Application to our network checkers game * the HARD PROBLEM: hidden spatial states - Information theoretic advisors - Combine with TD(O) - Open research questions.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 2003
Accession Number
ADA471681

Entities

People

  • Gregory Calbert
  • Hing-wah Kwok
  • Jason Scholz
  • Michael Webb
  • Peter Smet

Organizations

  • Defence Science and Technology Group

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Abstracts
  • Equations
  • Game Theory
  • Information Operations
  • Learning
  • Machine Learning
  • Markov Chains
  • Mathematics
  • Monte Carlo Method
  • Operations Research
  • Probability
  • Reconnaissance
  • Risk
  • Risk Analysis
  • Test And Evaluation
  • Vulnerability
  • War Games

Readers

  • Game Theory.
  • Human-Computer Interaction (HCI).
  • Mathematical Modeling and Probability Theory.