SOAR: An Architecture for General Intelligence

The ultimate goal of work in cognitive architecture is to provide the foundation for a system capable of general intelligent behavior. That is, the goal is to provide the underlying structure that would enable a system to perform the full range of cognitive tasks, employ the full range of problem-solving methods and representations appropriate for the tasks, and learn about all aspects of the tasks and its performance on them. In this article we present Soar, an implemented proposal for such an architecture. We describe its organizational principles, the system as currently implemented, and demonstrations of its capabilities. This research was sponsored by the Defense Advanced Research Projects Agency (DOD), ARPA Order No. 3597, monitored by the Air Force Avionics Laboratory under contracts F33615-81-K-1539 and NOOO39-83C-0136, and by the Personnel and Training Research Programs, Psychological Sciences Division, Office of Naval Research, under contract number N00014-82C-0067, contract authority identification number NR667-477. Additional partial support was provided by the Sloan Foundation and some computing support was supplied by the SUMEX-A1M facility (NIH grant number RR-00785). The views and conclusions contained in this document arc those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of die Defense Advanced Research Projects Agency, the Office of Naval Research, the Sloan Foundation, the National Institute of Health, or the US Government.