Symmetry-Invariant Novelty Heuristics via Unsupervised Weisfeiler-Leman Features

TL;DR

This paper introduces a novel approach using Weisfeiler-Leman Features to create symmetry-invariant novelty heuristics for planning, improving exploration efficiency by reducing redundant state evaluations.

Contribution

It proposes an unsupervised method to synthesize lifted, domain-independent novelty heuristics based on WLFs, addressing symmetry issues in existing heuristics.

Findings

Promising results on International Planning Competition benchmarks.

Effective reduction of redundant exploration due to symmetry invariance.

Potential for improved heuristic search performance.

Abstract

Novelty heuristics aid heuristic search by exploring states that exhibit novel atoms. However, novelty heuristics are not symmetry invariant and hence may sometimes lead to redundant exploration. In this preliminary report, we propose to use Weisfeiler-Leman Features for planning (WLFs) in place of atoms for detecting novelty. WLFs are recently introduced features for learning domain-dependent heuristics for generalised planning problems. We explore an unsupervised usage of WLFs for synthesising lifted, domain-independent novelty heuristics that are invariant to symmetric states. Experiments on the classical International Planning Competition and Hard To Ground benchmark suites yield promising results for novelty heuristics synthesised from WLFs.