Characterizing an Analogical Concept Memory for Architectures Implementing the Common Model of Cognition

TL;DR

This paper introduces an analogical concept memory for the Soar architecture, enabling rapid interactive concept learning that enhances recognition and action selection in cognitive agents.

Contribution

It presents a novel analogical memory system for Soar that improves concept acquisition from examples within interactive and embodied learning contexts.

Findings

The analogical memory enables quick learning of diverse novel concepts.

The system improves recognition and action selection in a simulated robotic domain.

The approach integrates with existing cognitive architectures for enhanced concept processing.

Abstract

Architectures that implement the Common Model of Cognition - Soar, ACT-R, and Sigma - have a prominent place in research on cognitive modeling as well as on designing complex intelligent agents. In this paper, we explore how computational models of analogical processing can be brought into these architectures to enable concept acquisition from examples obtained interactively. We propose a new analogical concept memory for Soar that augments its current system of declarative long-term memories. We frame the problem of concept learning as embedded within the larger context of interactive task learning (ITL) and embodied language processing (ELP). We demonstrate that the analogical learning methods implemented in the proposed memory can quickly learn a diverse types of novel concepts that are useful not only in recognition of a concept in the environment but also in action selection. Our approach has been instantiated in an implemented cognitive system \textsc{Aileen} and evaluated on a simulated robotic domain.