Investigating Transfer Learning in the Urban Combat Testbed

Abstract

We have developed a complex agent capable of transferring learned declarative knowledge between tasks in order to improve performance in a rich domain developed to test transfer performance "the Urban Combat Testbed". We present and discuss our experiments and results which demonstrate successful transfer learning. To better understand the underlying sources of transfer in this domain, we empirically evaluate the types of knowledge that contribute to the observed improvement in performance due to transfer, and discuss the implications of our analysis for general transfer learning research.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 10, 2007
Accession Number
ADA479071

Entities

People

  • John E. Laird
  • Nicholas A. Gorski

Organizations

  • University of Michigan

Tags

Communities of Interest

  • Autonomy
  • Counter IED
  • Energy and Power Technologies
  • Engineered Resilient Systems

DTIC Thesaurus Topics

  • Air Force Research Laboratories
  • Artificial Intelligence
  • Cognition
  • Computer Programs
  • Computers
  • Improvised Explosive Devices
  • Intelligent Agents
  • Learning
  • Machine Learning
  • Motion Planning
  • Navigation
  • New York
  • Psychology
  • Reinforcement Learning
  • Topology
  • United States Government
  • Video Games

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Combustion and Flow Dynamics.
  • Military Science and Technology Research and Modernization.