Characterizing the Performance of Applied Intelligent Agents in Soar

摘要

There have been a few efforts to evaluate the robustness of performance of the Soar cognitive architecture, with positive results. However, previous efforts have focused primarily on running the architecture with agent models that are research systems, designed specifically for Soar performance evaluation, or otherwise limited in capability. This paper reports an effort to take a number of applied intelligent agents "off the shelf" and use them for a further evaluation of Soar. One primary goal is to see whether the performance results for research systems also hold for applied agents. A second goal is to characterize Soar's "practical" ability to run applied, knowledge-rich agents with performance that will scale in number of agents, memory requirements, and execution time.