The Role of Higher-Order Cognitive Models in Active Learning

TL;DR

This paper explores how higher-order cognitive models can improve active learning systems that involve human feedback, emphasizing the importance of modeling human agency and recursive reasoning for better collaboration.

Contribution

It introduces a new paradigm for active learning that incorporates higher-order cognition and demonstrates its practical application and benefits through a computational study.

Findings

Higher levels of human agency lead to qualitatively different communication behaviors.

The proposed cognitive model produces unique and more effective active learning behaviors.

Empirical results show improved collaboration efficiency with higher-order modeling.

Abstract

Building machines capable of efficiently collaborating with humans has been a longstanding goal in artificial intelligence. Especially in the presence of uncertainties, optimal cooperation often requires that humans and artificial agents model each other's behavior and use these models to infer underlying goals, beliefs or intentions, potentially involving multiple levels of recursion. Empirical evidence for such higher-order cognition in human behavior is also provided by previous works in cognitive science, linguistics, and robotics. We advocate for a new paradigm for active learning for human feedback that utilises humans as active data sources while accounting for their higher levels of agency. In particular, we discuss how increasing level of agency results in qualitatively different forms of rational communication between an active learning system and a teacher. Additionally, we provide a practical example of active learning using a higher-order cognitive model. This is accompanied by a computational study that underscores the unique behaviors that this model produces.