Real-world planning problems often involve hundreds or even thousands of objects,
straining the limits of modern planners. In this work, we address this challenge by learning to …

We present three novel graph representations of planning tasks suitable for learning domain-
independent heuristics using Graph Neural Networks (GNNs) to guide search. In particular …

One of the oldest and most popular approaches to automated planning is to encode the
problem at hand into a propositional formula and use a Satisfiability (SAT) solver to find a …

Polynomial-time heuristic functions for planning are commonplace since 20 years. But
polynomial-time in which input? Almost all existing approaches are based on a grounded …

Recent research in classical planning has shown the importance of search techniques that
operate directly on the lifted representation of the problem, particularly in domains where the …

Planning models are usually defined in lifted, ie first order formalisms, while most solvers
need (variable-free) grounded representations. Though techniques for grounding prune …

Matrix multiplication is a fundamental operation of linear algebra, with applications ranging
from quantum physics to artificial intelligence. Given its importance, enormous resources …

Abstract Graph Neural Networks (GNNs) have become the standard method of choice for
learning with structured data, demonstrating particular promise in classical planning. Their …

While state-of-the-art planning systems need a grounded (propositional) task representation,
the input model is provided “lifted”, specifying predicates and action schemas with variables …

Classical planning instances are often represented using first-order logic; however, the
initial step for most classical planners is to transform the given instance into a propositional …