Learning Hierarchical Skills for Game Agents from Video of Human Behavior

Abstract

Developing autonomous agents for computer games is often a lengthy and expensive undertaking that requires manual encoding of detailed and complex knowledge. In this paper we show how to acquire hierarchical skills for controlling a team of simulated football players by observing video of college football play. We then demonstrate the results in the Rush 2008 football simulator, showing that the learned skills have high fidelity with respect to the observed video and are robust to changes in the environment. Finally, we conclude with discussions of this work and of possible improvements.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2009
Accession Number
ADA593080

Entities

People

  • Dan Shapiro
  • David J. Stracuzzi
  • David W. Aha
  • Gary Cleveland
  • Kamal Ali
  • Matthew Molineaux
  • Nan Li
  • Pat Langley
  • Tolga Konik

Organizations

  • Knexus Research (United States)

Tags

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Autonomous Agents
  • Computers
  • Environment
  • Human Behavior
  • Intelligent Agents
  • Learning
  • Machine Learning
  • Notation
  • Observation
  • Reinforcement Learning
  • Reliability
  • Simulations
  • Simulators
  • Universities
  • Video
  • Video Games

Fields of Study

  • Computer science

Readers

  • Game Theory.
  • Military Training and Readiness Simulation
  • Systems Analysis and Design