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 …

The merge-and-shrink framework has been introduced as a general approach for defining
abstractions of large state spaces arising in domain-independent planning and related …

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

The FastMap algorithm has been proposed as an inexpensive metric embedding which
provides admissible distance estimates between all vertices in an embedding. As an …

Abstraction heuristics are the state of the art in optimal classical planning as heuristic
search. A popular method for computing abstractions is the counterexample-guided …

PLANUTILS is a general library for setting up Linux-based environments for developing,
running, and evaluating planners. Over the last decades, the planning community has …

We propose a new approach based on ranking to learn to guide Greedy Best-First Search
(GBFS). As previous ranking approaches, ours is based on the observation that directly …

Current approaches for learning for planning have yet to achieve competitive performance
against classical planners in several domains, and have poor overall performance. In this …

Rubik's Cube (RC) is a well-known and computationally challenging puzzle that has
motivated AI researchers to explore efficient alternative representations and problem-solving …

This planner abstract describes “Scorpion 2023”, the planner configuration we submitted to
the sequential optimization track of the International Planning Competition 2023. Scorpion …