Advertisement

The Soar Architecture

  • John Laird
  • Paul Rosenbloom
  • Allen Newell
Part of the The Kluwer International Series in Engineering and Computer Science book series (SECS, volume 11)

Abstract

In this chapter we propose a problem-space architecture, called Soar; that implements universal subgoaling.4 Throughout this chapter we will verify that Soar satisfies the six requirements for universal subgoaling listed in Figure 1–4. Soar is a modification of the Soar1 architecture (Laird & Newell, 1983b). At appropriate places, we will contrast Soar to the Soar1 architecture.

Keywords

Task Operator Current Operator Problem Space Current Context Current Object 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Kluwer Academic Publishers 1986

Authors and Affiliations

  • John Laird
    • 1
  • Paul Rosenbloom
    • 2
  • Allen Newell
    • 3
  1. 1.Xerox Palo Alto Research CenterPalo AltoUSA
  2. 2.Stanford UniversityPalo AltoUSA
  3. 3.Carnegie-Mellon UniversityPittsburghUSA

Personalised recommendations