Introduction to Soar

TL;DR

This paper provides a comprehensive overview of the Soar cognitive architecture, detailing its structure, processing mechanisms, learning modules, and its potential for supporting general human-level AI.

Contribution

It offers a detailed architectural and functional overview of Soar version 9.6, highlighting its components, processing, and learning capabilities for the first time.

Findings

Describes the architecture and processing of Soar 9.6.

Details various learning modules including chunking and reinforcement learning.

Analyzes Soar's suitability for general human-level AI.

Abstract

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 memory, and spatial-visual reasoning. It then reviews the levels of decision making and variety of learning in Soar, and analysis of Soar as an architecture supporting general human-level AI. Following the references is an appendix that contains short descriptions of recent Soar agents and a glossary of the terminology we use in describing Soar.