Saved in:
Bibliographic Details
Main Authors: Knierim, Matilda, Jain, Sahil, Aydoğan, Murat Han, Mitra, Kenneth, Desai, Kush, Saran, Akanksha, Baraka, Kim
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.23554
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910678907879424
author Knierim, Matilda
Jain, Sahil
Aydoğan, Murat Han
Mitra, Kenneth
Desai, Kush
Saran, Akanksha
Baraka, Kim
author_facet Knierim, Matilda
Jain, Sahil
Aydoğan, Murat Han
Mitra, Kenneth
Desai, Kush
Saran, Akanksha
Baraka, Kim
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_23554
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Prosody as a Teaching Signal for Agent Learning: Exploratory Studies and Algorithmic Implications
Knierim, Matilda
Jain, Sahil
Aydoğan, Murat Han
Mitra, Kenneth
Desai, Kush
Saran, Akanksha
Baraka, Kim
Machine Learning
Human-Computer Interaction
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.
title Prosody as a Teaching Signal for Agent Learning: Exploratory Studies and Algorithmic Implications
topic Machine Learning
Human-Computer Interaction
url https://arxiv.org/abs/2410.23554