# A Unifying Bayesian Formulation of Measures of Interpretability in Human-AI

arXiv: https://arxiv.org/abs/2104.10743 · HTML: https://mlsanity.com/paper/2104.10743/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 38 references that are in the map.
- First posted on arXiv 21 Apr 2021.

## Builds on (most cited first, 10 of 10)

- [Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior](https://mlsanity.com/paper/1805.08010/) (2018)
- [Explicability? Legibility? Predictability? Transparency? Privacy? Security? The Emerging Landscape of Interpretable Agent Behavior](https://mlsanity.com/paper/1811.09722/) (2018)
- [Probabilistically Safe Robot Planning with Confidence-Based Human Predictions](https://mlsanity.com/paper/1806.00109/) (2018)
- [Plan Explicability and Predictability for Robot Task Planning](https://mlsanity.com/paper/1511.08158/) (2015)
- [A Unified Framework for Planning in Adversarial and Cooperative Environments](https://mlsanity.com/paper/1802.06137/) (2018)
- [Signaling Friends and Head-Faking Enemies Simultaneously: Balancing Goal Obfuscation and Goal Legibility](https://mlsanity.com/paper/1905.10672/) (2019)
- [Expectation-Aware Planning: A Unifying Framework for Synthesizing and Executing Self-Explaining Plans for Human-Aware Planning](https://mlsanity.com/paper/1903.07269/) (2019)
- [Designing Environments Conducive to Interpretable Robot Behavior](https://mlsanity.com/paper/2007.00820/) (2020)
- [Robot Planning with Mathematical Models of Human State and Action](https://mlsanity.com/paper/1705.04226/) (2017)
- [A Bayesian Account of Measures of Interpretability in Human-AI Interaction](https://mlsanity.com/paper/2011.10920/) (2020)

## Built on by (most cited first, 5 of 5)

- [Deceptive Decision-Making Under Uncertainty](https://mlsanity.com/paper/2109.06740/) (2021)
- [A Mental-Model Centric Landscape of Human-AI Symbiosis](https://mlsanity.com/paper/2202.09447/) (2022)
- [Planning for Attacker Entrapment in Adversarial Settings](https://mlsanity.com/paper/2303.00822/) (2023)
- [Human-Modeling in Sequential Decision-Making: An Analysis through the Lens of Human-Aware AI](https://mlsanity.com/paper/2405.07773/) (2024)
- [The Mirror Agent Model: a Bayesian Architecture for Interpretable Agent Behavior](https://mlsanity.com/paper/2609.05190/) (2026)

## Abstract (arXiv)

Existing approaches for generating human-aware agent behaviors have considered different measures of interpretability in isolation. Further, these measures have been studied under differing assumptions, thus precluding the possibility of designing a single framework that captures these measures under the same assumptions. In this paper, we present a unifying Bayesian framework that models a human observer's evolving beliefs about an agent and thereby define the problem of Generalized Human-Aware Planning. We will show that the definitions of interpretability measures like explicability, legibility and predictability from the prior literature fall out as special cases of our general framework. Through this framework, we also bring a previously ignored fact to light that the human-robot interactions are in effect open-world problems, particularly as a result of modeling the human's beliefs over the agent. Since the human may not only hold beliefs unknown to the agent but may also form new hypotheses about the agent when presented with novel or unexpected behaviors.