# Leveraging Counterfactual Paths for Contrastive Explanations of POMDP Policies

arXiv: https://arxiv.org/abs/2403.19760 · HTML: https://mlsanity.com/paper/2403.19760/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 22 references that are in the map.
- First posted on arXiv 28 Mar 2024.

## Builds on (most cited first, 7 of 7)

- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Explainable Deep Learning: A Field Guide for the Uninitiated](https://mlsanity.com/paper/2004.14545/) (2020)
- [DESPOT: Online POMDP Planning with Regularization](https://mlsanity.com/paper/1609.03250/) (2016)
- [What Does Explainable AI Really Mean? A New Conceptualization of Perspectives](https://mlsanity.com/paper/1710.00794/) (2017)
- [Not all users are the same: Providing personalized explanations for sequential decision making problems](https://mlsanity.com/paper/2106.12207/) (2021)
- [Collaborative Decision Making Using Action Suggestions](https://mlsanity.com/paper/2209.13160/) (2022)
- [Incorporating Human Path Preferences in Robot Navigation with Minimal Interventions](https://mlsanity.com/paper/2303.03530/) (2023)

## Abstract (arXiv)

As humans come to rely on autonomous systems more, ensuring the transparency of such systems is important to their continued adoption. Explainable Artificial Intelligence (XAI) aims to reduce confusion and foster trust in systems by providing explanations of agent behavior. Partially observable Markov decision processes (POMDPs) provide a flexible framework capable of reasoning over transition and state uncertainty, while also being amenable to explanation. This work investigates the use of user-provided counterfactuals to generate contrastive explanations of POMDP policies. Feature expectations are used as a means of contrasting the performance of these policies. We demonstrate our approach in a Search and Rescue (SAR) setting. We analyze and discuss the associated challenges through two case studies.