What do you think?
Rate this book
The Soar Cognitive Architecture
The definitive presentation of Soar, one AI's most enduring architectures, offering comprehensive descriptions of fundamental aspects and new components. 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.
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.
- GenresArtificial Intelligence
374 pages, Hardcover
First published April 13, 2012
3 people are currently reading
72 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 of 1 review
Read
May 5, 2016It took me a while to get around to finishing this, but it was a good read. The overarching theme is a set of about a dozen (hypothesized) requirements for general AI, and to what extent Soar fulfills these requirements through what functions.
The most elucidating to me was chapter 5, which explains how substates form the basis for complex behavior (they were sort of magical before).
Chapters 7-11 detail newer Soar functionality, including reinforcement learning, long-term memory, and visuo-spatial reasoning. Most of these chapters are condensed versions of recent dissertations, so each shows experimental results and avenues for future research. There's a lot of low hanging fruit, as well as opportunities for deep problem solving.
The most elucidating to me was chapter 5, which explains how substates form the basis for complex behavior (they were sort of magical before).
Chapters 7-11 detail newer Soar functionality, including reinforcement learning, long-term memory, and visuo-spatial reasoning. Most of these chapters are condensed versions of recent dissertations, so each shows experimental results and avenues for future research. There's a lot of low hanging fruit, as well as opportunities for deep problem solving.
Displaying 1 of 1 review