29 September 1987 | John E. Laird, Allen Newell and Paul S. Rosenbloom
Soar is an architecture for general intelligence, designed to enable a system to perform a wide range of cognitive tasks, use appropriate problem-solving methods and representations, and learn about all aspects of the tasks. The architecture is based on the idea that all tasks can be represented as problem spaces, and that knowledge is used to control search and learning. Soar has been implemented as an experimental software system and has been tested on a variety of tasks, including standard AI problems and expert systems. The architecture includes a production system for representing long-term knowledge, a working memory for storing current information, and a processing structure for executing tasks. The system also includes mechanisms for learning through experience, such as chunking, which allows the system to learn from past experiences and apply that knowledge to new situations. Soar is compared to other AI systems and is intended as the basis for a psychological theory of human cognition. The architecture has been tested on a variety of tasks and has shown the ability to learn and adapt to new situations. The system is designed to operate throughout the entire spectrum of cognitive tasks and is intended to provide a foundation for a system capable of general intelligent behavior.Soar is an architecture for general intelligence, designed to enable a system to perform a wide range of cognitive tasks, use appropriate problem-solving methods and representations, and learn about all aspects of the tasks. The architecture is based on the idea that all tasks can be represented as problem spaces, and that knowledge is used to control search and learning. Soar has been implemented as an experimental software system and has been tested on a variety of tasks, including standard AI problems and expert systems. The architecture includes a production system for representing long-term knowledge, a working memory for storing current information, and a processing structure for executing tasks. The system also includes mechanisms for learning through experience, such as chunking, which allows the system to learn from past experiences and apply that knowledge to new situations. Soar is compared to other AI systems and is intended as the basis for a psychological theory of human cognition. The architecture has been tested on a variety of tasks and has shown the ability to learn and adapt to new situations. The system is designed to operate throughout the entire spectrum of cognitive tasks and is intended to provide a foundation for a system capable of general intelligent behavior.