Behaviorally Modeling Games of Strategy Using Descriptive Q-learning

Abstract

Modeling human decision making in strategic problem domains is challenging with normative game theoretic approaches. Behavioral aspects of this type of decision making, such as forgetfulness or misattribution of reward, require additional parameters to capture their effect on decisions. We propose a descriptive model utilizing aspects of behavioral game theory, machine learning, and prospect theory that replicates the behavior of humans in uncertain strategic environments. We test the predictive capabilities of this model over data from 43 participants guiding a simulated Uninhabited Aerial Vehicle (UAV) against an unknown automated opponent.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2013
Accession Number
ADA575140

Entities

People

  • Adam Goodie
  • Dan Hall
  • Matthew Meisel
  • Prashant Doshi
  • Roi Ceren

Organizations

  • University of Georgia Research Foundation

Tags

Communities of Interest

  • Autonomy
  • Human Systems

DTIC Thesaurus Topics

  • Aircrafts
  • Algorithms
  • Artificial Intelligence
  • Computational Modeling
  • Data Sets
  • Environment
  • Game Theory
  • Learning
  • Machine Learning
  • Probability
  • Reinforcement Learning
  • Sequential Games
  • Simplex Method
  • Simulations
  • Trajectories
  • Unmanned Aerial Vehicles
  • Weighting Functions

Fields of Study

  • Computer science
  • Psychology

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Organizational Psychology.
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Neural Networks