Characterizing an Analogical Concept Memory for Architectures Implementing the Common Model of Cognition
This work addresses concept learning for cognitive modeling and intelligent agents, but it is incremental as it builds on existing architectures and analogical processing methods.
The paper tackles the problem of enabling concept acquisition from interactive examples in cognitive architectures by proposing a new analogical concept memory for Soar, demonstrating that it can quickly learn diverse novel concepts useful for recognition and action selection in a simulated robotic domain.
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.