Chunking in SOAR: The Anatomy of a General Learning Mechanism.

Abstract

In this article we describe an approach to the construction of a general learning mechanism based on chunking in SOAR. chunking is a learning mechanism that acquires rules from goal-based experience. SOAR is a general problem-solving architecture with a rule-based memory. In previous work we have demonstrated how the combination of chunking and SOAR could acquire serch-control knowledge (strategy acquisition) and operator implementation rules in both search-based puzzle tasks and knowledge-based expert-system tasks. In this work we examine the anatomy of chunking in SOAR and provide a new demonstration of its learning capabilities involving the acquisition and use of macro-operators. Keywords: Machine Learning, chunking.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 1985
Accession Number
ADA169359

Entities

People

  • Allen Newell
  • John E. Laird
  • Paul Simon Rosenbloom

Organizations

  • PARC

Tags

Communities of Interest

  • Autonomy
  • Biomedical
  • C4I
  • Cyber
  • Human Systems

DTIC Thesaurus Topics

  • Acquisition
  • Anatomy
  • Applied Psychology
  • Artificial Intelligence
  • Biological Sciences
  • California
  • Cells
  • Cognitive Science
  • Computer Science
  • Computers
  • Educational Technology
  • Expert Systems
  • Law
  • Machine Learning
  • Military Research
  • New York
  • Psychology

Readers

  • Artificial Intelligence

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval