# Pointwise-in-Time Explanation for Linear Temporal Logic Rules

arXiv: https://arxiv.org/abs/2306.13956 · HTML: https://mlsanity.com/paper/2306.13956/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 51 references that are in the map.
- First posted on arXiv 24 Jun 2023.

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

- [The Emerging Landscape of Explainable AI Planning and Decision Making](https://mlsanity.com/paper/2002.11697/) (2020)
- [Learning Linear Temporal Properties](https://mlsanity.com/paper/1806.03953/) (2018)
- [Explaining Multi-stage Tasks by Learning Temporal Logic Formulas from Suboptimal Demonstrations](https://mlsanity.com/paper/2006.02411/) (2020)
- [Learning Interpretable Temporal Properties from Positive Examples Only](https://mlsanity.com/paper/2209.02650/) (2022)
- [Learning Linear Temporal Properties from Noisy Data: A MaxSAT Approach](https://mlsanity.com/paper/2104.15083/) (2021)
- [Toward Policy Explanations for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2204.12568/) (2022)
- [Visualizing Robot Intent for Object Handovers with Augmented Reality](https://mlsanity.com/paper/2103.04055/) (2021)
- [Inferring Temporal Logic Properties from Data using Boosted Decision Trees](https://mlsanity.com/paper/2105.11508/) (2021)
- [A Counting Semantics for Monitoring LTL Specifications over Finite Traces](https://mlsanity.com/paper/1804.03237/) (2018)

## Built on by (most cited first, 1 of 1)

- ["What are my options?": Explaining RL Agents with Diverse Near-Optimal Alternatives (Extended)](https://mlsanity.com/paper/2506.09901/) (2025)

## Abstract (arXiv)

The new field of Explainable Planning (XAIP) has produced a variety of approaches to explain and describe the behavior of autonomous agents to human observers. Many summarize agent behavior in terms of the constraints, or ''rules,'' which the agent adheres to during its trajectories. In this work, we narrow the focus from summary to specific moments in individual trajectories, offering a ''pointwise-in-time'' view. Our novel framework, which we define on Linear Temporal Logic (LTL) rules, assigns an intuitive status to any rule in order to describe the trajectory progress at individual time steps; here, a rule is classified as active, satisfied, inactive, or violated. Given a trajectory, a user may query for status of specific LTL rules at individual trajectory time steps. In this paper, we present this novel framework, named Rule Status Assessment (RSA), and provide an example of its implementation. We find that pointwise-in-time status assessment is useful as a post-hoc diagnostic, enabling a user to systematically track the agent's behavior with respect to a set of rules.