Varieties of Learning in Soar: 1987

Abstract

Soar is an architecture for intelligence that integrates learning into all of its problem-solving behavior. The learning mechanism, chunking, has been studied experimentally in a broad range of tasks and situations. This paper summarizes the research on chucking in Soar, covering the effects of chunking in different tasks, task-independent applications of chunking and our theoretical analyses of effects and limits of chunking. We discuss what and when Soar has been able to learn so far. The results demonstrate that the variety of learning in Soar arises from variety in problem solving, rather than from variety in architectural mechanisms. Keywords: Artificial intelligence, Machine learning, cognitive architecture.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 29, 1987
Accession Number
ADA204680

Entities

People

  • A. Golding
  • A. Newell
  • A. Unruh
  • D. M. Steir
  • G. R. Yost
  • J. E. Laird
  • O. G. Shivers
  • P. S. Rosenbloom
  • R. A. Flynn
  • T. A. Polk

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Autonomy
  • Biomedical
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Acquisition
  • Applied Computer Science
  • Artificial Intelligence
  • Automata Theory
  • Cognitive Science
  • Computer Programming
  • Computer Science
  • Computers
  • Engineering
  • Language
  • Machine Learning
  • Natural Languages
  • Psychology
  • Reaction Time
  • Recognition
  • United States
  • Universities

Readers

  • STEM Education
  • Theoretical Analysis.
  • ballistics.

Technology Areas

  • AI & ML