Extending the Soar Cognitive Architecture

By John Edwin Laird. Artificial General Intelligence, 2008

418 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Measuring universal intelligence: Towards an anytime intelligence test (2010, background): “For instance, Soar [25,26], one of the most successful and well-known cognitive architectures in artificial intelligence, implicitly assumes some features about agents and environments.”
Cognitive architectures: Research issues and challenges (2009, background): “Soar (Laird, 2008; Laird, Newell, & Rosenbloom, 1987; Newell, 1990) is a cognitive architecture that has been under continuous development since the early 1980s.”
Learning to play (2009, background): “Soar [3] is a symbolic cognitive architecture that has been extensively used in designing intelligent agents across various domains.”
Using Imagery to Simplify Perceptual Abstraction in Reinforcement Learning Agents (2010, methodology): “Our solution to this problem is implemented using the Soar cognitive architecture (Laird, 2008), which has recently been augmented with specialized processing for spatial information (Wintermute, 2009b).”