# Closed-loop Teaching via Demonstrations to Improve Policy Transparency

arXiv: https://arxiv.org/abs/2406.11850 · HTML: https://mlsanity.com/paper/2406.11850/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 31 references that are in the map.
- First posted on arXiv 1 Apr 2024.

## Builds on (most cited first, 9 of 9)

- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Visualizing and Understanding Atari Agents](https://mlsanity.com/paper/1711.00138/) (2017)
- [Explainable Reinforcement Learning: A Survey](https://mlsanity.com/paper/2005.06247/) (2020)
- [Establishing Appropriate Trust via Critical States](https://mlsanity.com/paper/1810.08174/) (2018)
- [Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions](https://mlsanity.com/paper/2002.03478/) (2020)
- [Enabling Robots to Communicate their Objectives](https://mlsanity.com/paper/1702.03465/) (2017)
- [Exploring Computational User Models for Agent Policy Summarization](https://mlsanity.com/paper/1905.13271/) (2019)
- [Reasoning about Counterfactuals to Improve Human Inverse Reinforcement Learning](https://mlsanity.com/paper/2203.01855/) (2022)
- [Adapting sample size in particle filters through KLD-resampling](https://mlsanity.com/paper/1306.3172/) (2013)

## Abstract (arXiv)

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.