Communication Dans Un Congrès Année : 2024

Graph Learning for Numeric Planning

Résumé

Graph learning is naturally well suited for use in symbolic, object-centric planning due to its ability to exploit relational structures exhibited in planning domains and to take as input planning instances with arbitrary numbers of objects. Numeric planning is an extension of symbolic planning in which states may now also exhibit numeric variables. In this work, we propose data-efficient and interpretable machine learning models for learning to solve numeric planning tasks. This involves constructing a new graph kernel for graphs with both continuous and categorical attributes, as well as new optimisation methods for learning heuristic functions for numeric planning. Experiments show that our graph kernels are vastly more efficient and generalise better than graph neural networks for numeric planning, and also yield competitive coverage performance compared to domain-independent numeric planners. Code is available at https://github.com/DillonZChen/goose
Fichier sous embargo
Fichier sous embargo
0 5 29
Année Mois Jours
Avant la publication
mercredi 30 juillet 2025
Fichier sous embargo
mercredi 30 juillet 2025
Connectez-vous pour demander l'accès au fichier

Dates et versions

hal-04919158 , version 1 (30-01-2025)

Licence

Identifiants

  • HAL Id : hal-04919158 , version 1

Citer

Dillon Z Chen, Sylvie Thiébaux. Graph Learning for Numeric Planning. Annual Conference on Neural Information Processing Systems (NeurIPS-24), Dec 2024, Vancouver (BC), Canada. ⟨hal-04919158⟩
0 Consultations
0 Téléchargements

Partager

More