The Soar Cognitive Architecture


In development for thirty years, Soar is a general cognitive architecture that integrates knowledge-intensive reasoning, reactive execution, hierarchical reasoning, planning, and learning from experience, with the goal of creating a general computational system that has the same cognitive abilities as humans. In contrast, most AI systems are designed to solve only one type of problem, such as playing chess, searching the Internet, or scheduling aircraft departures. Soar is both a software system for agent development and a theory of what computational structures are necessary to support human-level agents. Over the years, both software system and theory have evolved. This book offers the definitive presentation of Soar from theoretical and practical perspectives, providing comprehensive descriptions of fundamental aspects and new components.

The current version of Soar features major extensions, adding reinforcement learning, semantic memory, episodic memory, mental imagery, and an appraisal-based model of emotion. This book describes details of Soar's component memories and processes and offers demonstrations of individual components, components working in combination, and real-world applications. Beyond these functional considerations, the book also proposes requirements for general cognitive architectures and explicitly evaluates how well Soar meets those requirements.

Table of Contents

  1. Preface
  2. Acknowledgments
  3. 1. Introduction
  4. 2. Requirements for Cognitive Architectures
  5. 3. The Problem-Space Computational Model
  6. 4. Soar as an Implementation of the PSCM
  7. 5. Impasses and Substates: The Basis for Complex Reasoning
  8. 6. Chunking
  9. 7. Tuning Procedural Knowledge: Reinforcement Learning
  10. 8. Semantic Memory

    Yongjia Wang and Nate Derbinsky

  11. 9. Episodic Memory

    Andrew M. Nuxoll and Nate Derbinsky

  12. 10. Visuospatial Processing with Mental Imagery

    Scott Lathrop and Samuel Wintermute

  13. 11. Emotion

    Robert P. Marinier III

  14. 12. Demonstrations of Multiple Architectural Capabilities

    Nate Derbinsky, Nicholas Gorski, Samuel Wintermute, and Joseph Xu

  15. 13. Soar Applications

    Robert E. Wray III

  16. 14. Conclusion
  17. References
  18. Index