Extracting Hierarchical Task Networks Parameters from Demonstrations - LAAS - Laboratoire d'Analyse et d'Architecture des Systèmes Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Extracting Hierarchical Task Networks Parameters from Demonstrations

Résumé

Hierarchical Task Networks (HTNs) are a common formalism in automated planning. However, HTN models are mostly designed by hand by expert users. While many of the state-ofthe-art approaches for learning HTN try and learn the structure and its parameterization in a single step, other focus specifically on learning the structure of the model. Many of these structure-focused approaches, however, learn models with non-parameterized actions, task and methods, which limits their generalization capabilities. In this paper, we propose a constraint satisfaction-based approach for extracting parameters for a given HTN structure using a set of demonstration traces.
Fichier principal
Vignette du fichier
2023-08-01_HAL.pdf (275.33 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04174929 , version 1 (01-08-2023)

Identifiants

  • HAL Id : hal-04174929 , version 1

Citer

Philippe Hérail, Arthur Bit-Monnot. Extracting Hierarchical Task Networks Parameters from Demonstrations. ICAPS Hierarchical Planning Workshop (HPlan), Jul 2023, Prague, Czech Republic. ⟨hal-04174929⟩
19 Consultations
18 Téléchargements

Partager

Gmail Facebook X LinkedIn More