Learning Interpretable Classifiers for PDDL Planning
This work addresses the need for interpretable behavior classifiers in planning domains, though it is incremental as it builds on existing logic-based methods.
The paper tackles the problem of synthesizing interpretable models that recognize an agent's behavior in PDDL planning tasks by learning logical formulas in First-Order Temporal Logic from examples, showing that learning is NP-hard but can be done via MaxSAT compilation to produce accurate formulas in reasonable time.
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.