# Learning Interpretable Classifiers for PDDL Planning

arXiv: https://arxiv.org/abs/2410.10011 · HTML: https://mlsanity.com/paper/2410.10011/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 29 references that are in the map.
- First posted on arXiv 13 Oct 2024.

## Builds on (most cited first, 8 of 8)

- [A C-LSTM Neural Network for Text Classification](https://mlsanity.com/paper/1511.08630/) (2015)
- [Learning Linear Temporal Properties](https://mlsanity.com/paper/1806.03953/) (2018)
- [Learning Features and Abstract Actions for Computing Generalized Plans](https://mlsanity.com/paper/1811.07231/) (2018)
- [Interpretable Sequence Classification via Discrete Optimization](https://mlsanity.com/paper/2010.02819/) (2020)
- [The Complexity of Learning Linear Temporal Formulas from Examples](https://mlsanity.com/paper/2102.00876/) (2021)
- [Learning Linear Temporal Properties from Noisy Data: A MaxSAT Approach](https://mlsanity.com/paper/2104.15083/) (2021)
- [Scalable Anytime Algorithms for Learning Fragments of Linear Temporal Logic](https://mlsanity.com/paper/2110.06726/) (2021)
- [Learning temporal formulas from examples is hard](https://mlsanity.com/paper/2312.16336/) (2023)

## Abstract (arXiv)

We consider the problem of synthesizing interpretable models that recognize the behaviour of an agent compared to other agents, on a whole set of similar planning tasks expressed in PDDL. Our approach consists in learning logical formulas, from a small set of examples that show how an agent solved small planning instances. These formulas are expressed in a version of First-Order Temporal Logic (FTL) tailored to our planning formalism. Such formulas are human-readable, serve as (partial) descriptions of an agent's policy, and generalize to unseen instances. We show that learning such formulas is computationally intractable, as it is an NP-hard problem. As such, we propose to learn these behaviour classifiers through a topology-guided compilation to MaxSAT, which allows us to generate a wide range of different formulas. Experiments show that interesting and accurate formulas can be learned in reasonable time.