Closed-loop Teaching via Demonstrations to Improve Policy Transparency

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Michael S., Simmons, Reid, Admoni, Henny
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910491645837312
author Lee, Michael S.
Simmons, Reid
Admoni, Henny
author_facet Lee, Michael S.
Simmons, Reid
Admoni, Henny
contents Demonstrations are a powerful way of increasing the transparency of AI policies. Though informative demonstrations may be selected a priori through the machine teaching paradigm, student learning may deviate from the preselected curriculum in situ. This paper thus explores augmenting a curriculum with a closed-loop teaching framework inspired by principles from the education literature, such as the zone of proximal development and the testing effect. We utilize tests accordingly to close to the loop and maintain a novel particle filter model of human beliefs throughout the learning process, allowing us to provide demonstrations that are targeted to the human's current understanding in real time. A user study finds that our proposed closed-loop teaching framework reduces the regret in human test responses by 43% over a baseline.
format Preprint
id arxiv_https___arxiv_org_abs_2406_11850
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Closed-loop Teaching via Demonstrations to Improve Policy Transparency
Lee, Michael S.
Simmons, Reid
Admoni, Henny
Computers and Society
Artificial Intelligence
Demonstrations are a powerful way of increasing the transparency of AI policies. Though informative demonstrations may be selected a priori through the machine teaching paradigm, student learning may deviate from the preselected curriculum in situ. This paper thus explores augmenting a curriculum with a closed-loop teaching framework inspired by principles from the education literature, such as the zone of proximal development and the testing effect. We utilize tests accordingly to close to the loop and maintain a novel particle filter model of human beliefs throughout the learning process, allowing us to provide demonstrations that are targeted to the human's current understanding in real time. A user study finds that our proposed closed-loop teaching framework reduces the regret in human test responses by 43% over a baseline.
title Closed-loop Teaching via Demonstrations to Improve Policy Transparency
topic Computers and Society
Artificial Intelligence
url https://arxiv.org/abs/2406.11850