Introduction to Soar

  title={Introduction to Soar},
  author={John E. Laird},
  • J. Laird
  • Published 8 May 2022
  • Computer Science
  • ArXiv
This paper is the recommended initial reading for a functional overview of Soar, version 9.6. It includes an abstract overview of the architectural structure of Soar including its processing, memories, learning modules, their interfaces, and the representations of knowledge used by those modules. From there it describes the processing supported by those modules, including decision making, impasses and substates, procedure learning via chunking, reinforcement learning, semantic memory, episodic… 

Figures from this paper



Unified Theories of Cognition

Using diverse cognitive mechanisms for action modeling

A taskindependent framework based on the Soar cognitive architecture is described in which rules, episodic memory, semantic memory, mental imagery, and task decomposition are available for predicting an action’s consequences.

Using Imagery to Simplify Perceptual Abstraction in Reinforcement Learning Agents

This paper considers the problem of reinforcement learning in spatial tasks, and shows that this integration with an imagery system broadens the class of perceptual abstraction methods that can be used while preserving the underlying problem.

The Soar Cognitive Architecture

  • J. Laird
  • Computer Science, Psychology
  • 2012
This book offers the definitive presentation of Soar from theoretical and practical perspectives, providing comprehensive descriptions of fundamental aspects and new components, and proposes requirements for general cognitive architectures and explicitly evaluates how well Soar meets those requirements.

A computational unification of cognitive behavior and emotion

An integrated theory of the mind.

The perceptual-motor modules, the goal module, and the declarative memory module are presented as examples of specialized systems in ACT-R, which consists of multiple modules that are integrated to produce coherent cognition.

A Standard Model for the Mind: Toward a Common

  • Mind Matters,
  • 2017

An Analysis and Comparison of ACT-R and Soar

  • J. Laird
  • Computer Science, Psychology
  • 2022
This is a detailed analysis and comparison of the ACT-R and Soar cognitive architectures, including their overall structure, their representations of agent data and metadata, and their associated

A Comprehensive Computational Model of PRIMs Theory for Task-Independent Procedural Learning

A novel form of primitive processing is introduced that explains the origins of PRIM procedures and supports procedural learning in an unbounded, dynamic working memory space and a novel computational approach by which a cognitive architecture model can learn to guide long-term declarative memory retrievals based on task context is introduced.