Closed-loop Teaching via Demonstrations to Improve Policy Transparency
This work addresses the challenge of making AI policies more transparent for human learners, though it is incremental as it builds on existing machine teaching and education principles.
The paper tackles the problem of improving AI policy transparency through demonstrations by introducing a closed-loop teaching framework that adapts to the learner's understanding in real time, resulting in a 43% reduction in regret in human test responses compared to a baseline.
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.