Prosody as an Informative Teaching Signal for Agent Learning: Exploratory Studies and Algorithmic Implications

Akanksha Saran

Matilda Knierim

Sahil Jain

Murat Han Aydoğan

Kenneth Mitra

Kush Desai

Kim Baraka

ICMI 2024

2024

Abstract

Agent learning from human interaction often relies on explicit signals, but implicit social cues, such as prosody in speech, could provide valuable information for more effective learning. This paper
advocates for the integration of prosody as a teaching signal to enhance agent learning from human teachers. Through two exploratory studies—one examining voice feedback in an interactive reinforcement learning setup and the other analyzing restricted audio from human demonstrations in three Atari games—we demonstrate that prosody carries significant information about task dynamics.
Our findings suggest that prosodic features, when coupled with explicit feedback, can enhance reinforcement learning outcomes. Moreover, we propose guidelines for prosody-sensitive algorithm
design and discuss insights into teaching behavior. Our work underscores the potential of leveraging prosody as an implicit signal for more efficient agent learning, thus advancing human-agent interaction paradigms.