Prosody as a Teaching Signal for Agent Learning: Exploratory Studies and Algorithmic Implications
This work addresses the challenge of improving agent learning efficiency for human-agent interaction, though it appears incremental as it builds on existing reinforcement learning frameworks.
The paper tackles the problem of agent learning from human interaction by exploring prosody in speech as an implicit teaching signal, demonstrating through studies that prosodic features can enhance reinforcement learning outcomes when combined with explicit feedback.
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.