Compact Tree Encodings for Planning as QBF - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Inteligencia Artificial. Ibero-American Journal of Artificial Intelligence Année : 2018

Compact Tree Encodings for Planning as QBF

Résumé

Considerable improvements in the technology and performance of SAT solvers has made their use possible for the resolution of various problems in artificial intelligence, and among them that of generating plans. Recently, promising Quantified Boolean Formula (QBF) solvers have been developed and we may expect that in a near future they become as efficient as SAT solvers. So, it is interesting to use QBF language that allows us to produce more compact encodings. We present in this article a translation from STRIPS planning problems into quantified propositional formulas. We introduce two new Compact Tree Encodings: CTE-EFA based on Explanatory frame axioms, and CTE-OPEN based on causal links. Then we compare both of them to CTE-NOOP based on No-op Actions proposed in [Cashmore et al. 2012]. In terms of execution time over benchmark problems, CTE-EFA and CTE-OPEN always performed better than CTE-NOOP.
Fichier principal
Vignette du fichier
gasquet_22544.pdf (566.82 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02181997 , version 1 (12-07-2019)

Identifiants

  • HAL Id : hal-02181997 , version 1
  • OATAO : 22544

Citer

Olivier Gasquet, Dominique Longin, Frédéric Maris, Pierre Régnier, Maël Valais. Compact Tree Encodings for Planning as QBF. Inteligencia Artificial. Ibero-American Journal of Artificial Intelligence, 2018, 21 (62), pp.103-113. ⟨hal-02181997⟩
48 Consultations
71 Téléchargements

Partager

Gmail Facebook X LinkedIn More