Research Catalog

Title

The Soar cognitive architecture / John E. Laird.

Author

Laird, John, 1954-

Publication

Cambridge, Mass. ; London, England : MIT Press, ©2012.

Items in the Library & Off-site

Details

Description

xv, 374 p. : ill.; 24 cm.

Summary

"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."--Publisher.

Subject

• Artificial intelligence
• Software architecture
• Artificial Intelligence
• artificial intelligence
• Künstliche Intelligenz
• Softwarearchitektur

Note

• "A Bradford Book."

Bibliography (note)

• Includes bibliographical references (p. [347]-366) and index.

Contents

1. Introduction -- 1.1. Background -- 1.2. Cognitive Architectures -- 1.3. Soar -- 1.4. Research Strategy -- 1.5. Preview of Chapters 2-14 -- 2. Requirements for Cognitive Architectures -- 2.1. Characteristics of Environments, Tasks, and Agents -- 2.2. Architectural Requirements -- 3. The Problem-Space Computational Model -- 3.1. Task Environments -- 3.2. The Problem-Space Framework -- 3.3. Knowledge Search -- 3.4. Problem-Space Computational Models -- 3.5. Impasses and Substates -- 3.6. Using Multiple Sources of Knowledge -- 3.7. Acquiring Knowledge -- 3.8. Alternative PSCMs -- 4. Soar as an Implementation of the PSCM -- 4.1. Production Systems -- 4.2. Mapping Production Systems onto the PSCM -- 4.3. The Soar Processing Cycle -- 4.4. Demonstrations of Basic PSCM -- 4.5. Discussion -- 4.6. Analysis of Requirements -- 5. Impasses and Substates: The Basis for Complex Reasoning -- 5.1. Impasses -- 5.2. Substates -- 5.3. Problem Solving in Substates -- 5.4. Substate Results -- 5.5. Maintaining Consistency -- 5.6. Demonstrations of Impasses and Substates -- 5.7. Discussion -- 5.8. Analysis of Requirements -- 6. Chunking -- 6.1. Chunking in Soar -- 6.2. Implications of Chunking in Soar -- 6.3. Demonstrations of Chunking -- 6.4. Assumptions Inherent to Chunking -- 6.5. Analysis of Requirements -- 7. Tuning Procedural Knowledge: Reinforcement Learning -- 7.1. Reinforcement Learning in Soar -- 7.2. Learning over Large State Spaces -- 7.3. Demonstrations of Reinforcement Learning -- 7.4. Analysis of Requirements -- 8. Semantic Memory -- 8.1. Semantic Memory in Soar -- 8.2. Encoding and Storage -- 8.3. Retrieval -- 8.4. Demonstrations of Semantic Memory -- 8.5. Analysis of Requirements -- 9. Episodic Memory -- 9.1. Episodic Memory in Soar -- 9.2. Encoding and Storage -- 9.3. Retrieval -- 9.4. Use of Episodic Memory -- 9.5. Demonstrations of Episodic Memory -- 9.6. Comparison of Episodic Memory and Semantic Memory -- 9.7. Analysis of Requirements -- 10. Visuospatial Processing with Mental Imagery -- 10.1. Visual and Spatial Representations -- 10.2. Visuospatial Domains -- 10.3. SVS -- 10.4. Demonstrations of Spatial and Visual Imagery -- 10.5. Analysis of Requirements -- 11. Emotion -- 11.1. Appraisal Theories of Emotion -- 11.2. Abstract Functional Cognitive Operations -- 11.3. Unifying Cognitive Control and Appraisal -- 11.4. Emotion, Mood, and Feeling -- 11.5. Emotion and Reinforcement Learning -- 11.6. Demonstrations of Emotion Processing -- 11.7. Analysis of Requirements -- 12. Demonstrations of Multiple Architectural Capabilities -- 12.1. Learning to Use Episodic Memory with Reinforcement Learning -- 12.2. Using Mental Imagery with Reinforcement Learning -- 12.3. Diverse Forms of Action Modeling -- 12.4. Analysis of Requirements -- 13. Soar Applications -- 13.1. Applications -- 13.2. TacAir-Soar -- 13.3. Imagining TacAir-Soar 2.0 -- 14. Conclusion -- 14.1. Soar from a Structural Perspective -- 14.2. Soar from a Functional Perspective -- 14.3. Evaluating Soar on Architectural Requirements.

ISBN

• 9780262122962
• 0262122960

LCCN

2011030567

OCLC

• ocn748290725
• 748290725
• SCSB-9150157

Owning Institutions

Princeton University Library