Introduction

Go backward to Preface.
Go up to Top.
Go forward to The Problem Space Level.

Introduction
************

Soar has been developed to be a general cognitive architecture.  It has been
in use since 1983, evolving through many different versions to where it is
now Soar, Version 6.

Our goals for Soar include that it is to be an architecture that can:

   * work on the full range of tasks expected of an intelligent agent, from
     highly routine to extremely difficult, open-ended problems;
     
   * represent and use appropriate forms of knowledge, such as procedural,
     declarative, episodic, and possibly iconic;
     
   * employ the full range of problem solving methods;
     
   * interact with the outside world; and
     
   * learn about all aspects of the tasks and its performance on them.

In other words, our intention is for Soar to support all the capabilities
required of a general intelligent agent.

The ultimate in intelligence would be complete rationality which would
include the ability to use all available knowledge for every task that the
system encounters.  Unfortunately, if the body of knowledge is sufficiently
large, the tasks are sufficiently diverse, and the system must respond in a
sufficiently limited amount of time, this goal is impossible because of the
computational complexity involved in retrieving the relevant knowledge.  The
best that can be obtained is an approximation of complete rationality.  The
design of Soar can be seen as an investigation of one such approximation.
Below are the major principles that are the cornerstones of Soar's design and
its attempt to approximate rational behavior.

  1. The number of distinct architectural mechanisms should be minimized.  In
     Soar there is a single framework for all tasks and subtasks (problem
     spaces), a single representation of permanent knowledge (productions), a
     single representation of temporary knowledge (objects with attributes
     and values), a single mechanism for generating goals (automatic
     subgoaling), and a single learning mechanism (chunking).
     
  2. All decisions are made through the combination of relevant knowledge at
     run-time.  In Soar, every decision is based on the current
     interpretation of sensory data and any relevant knowledge retrieved from
     permanent memory.  Decisions are never precompiled into uninterruptible
     sequences.
Menu
