# "Guess what I'm doing": Extending legibility to sequential decision tasks

arXiv: https://arxiv.org/abs/2209.09141 · HTML: https://mlsanity.com/paper/2209.09141/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 51 references that are in the map.
- First posted on arXiv 19 Sep 2022.

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

- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Enabling Robots to Communicate their Objectives](https://mlsanity.com/paper/1702.03465/) (2017)
- [Explicability? Legibility? Predictability? Transparency? Privacy? Security? The Emerging Landscape of Interpretable Agent Behavior](https://mlsanity.com/paper/1811.09722/) (2018)
- [Expressing Robot Incapability](https://mlsanity.com/paper/1810.08167/) (2018)
- [Goal Recognition as Reinforcement Learning](https://mlsanity.com/paper/2202.06356/) (2022)
- [Encouraging Human Interaction with Robot Teams: Legible and Fair Subtask Allocations](https://mlsanity.com/paper/2205.03477/) (2022)

## Built on by (most cited first, 2 of 2)

- [Active Legibility in Multiagent Reinforcement Learning](https://mlsanity.com/paper/2410.20954/) (2024)
- ["Teammates, Am I Clear?": Analysing Legible Behaviours in Teams](https://mlsanity.com/paper/2507.21631/) (2025)

## Abstract (arXiv)

In this paper we investigate the notion of legibility in sequential decision tasks under uncertainty. Previous works that extend legibility to scenarios beyond robot motion either focus on deterministic settings or are computationally too expensive. Our proposed approach, dubbed PoL-MDP, is able to handle uncertainty while remaining computationally tractable. We establish the advantages of our approach against state-of-the-art approaches in several simulated scenarios of different complexity. We also showcase the use of our legible policies as demonstrations for an inverse reinforcement learning agent, establishing their superiority against the commonly used demonstrations based on the optimal policy. Finally, we assess the legibility of our computed policies through a user study where people are asked to infer the goal of a mobile robot following a legible policy by observing its actions.