Long-Term Symbolic Learning in Soar and ACT-R

Abstract

The characteristics of long-term, symbolic learning were investigated using Soar and ACT-R models of a task to rearrange blocks into specific configurations. Long sequences of problems were run collecting data to answer fundamental questions about long-term, symbolic learning. The questions were whether symbolic learning continues indefinitely, how learned knowledge is used, and whether performance degrades over the long term. It was found that in both systems symbolic learning eventually stopped, ACT-R produced three observable phases of learning, and both Soar and ACT-R suffer from the utility problem of degraded performance with continuous on-line learning.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2007
Accession Number
ADA478972

Entities

People

  • J. Gregory Trafton
  • William G. Kennedy

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Acquisition
  • Artificial Intelligence
  • Cognition
  • Cognitive Science
  • Computer Programming
  • Computers
  • Correlation Analysis
  • Information Processing
  • Information Science
  • Lisp Programming Language
  • Machine Learning
  • Military Research
  • Motor Skills
  • Operating Systems
  • Psychology

Readers

  • Artificial Intelligence
  • Educational Psychology