Knowledge extraction from learning traces in continuous domains - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Knowledge extraction from learning traces in continuous domains

Résumé

A method is introduced to extract and transfer knowledge between a source and a target task in continuous domains and for direct policy search algorithms. The principle is (1) to use a direct policy search on the source task, (2) extract knowledge from the learning traces and (3) transfer this knowledge with a reward shaping approach. The knowledge extraction process consists in analyzing the learning traces, i.e. the behaviors explored while learning on the source task, to identify the behavioral features specific to successful solutions. Each behavioral feature is then attributed a value corresponding to the average reward obtained by the individuals exhibiting it. These values are used to shape rewards while learning on a target task. The approach is tested on a simulated ball collecting task in a continuous arena. The behavior of an individual is analyzed with the help of the generated knowledge bases.
Fichier principal
Vignette du fichier
2014ACTI3227.pdf (643.63 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02987425 , version 1 (03-11-2020)

Identifiants

  • HAL Id : hal-02987425 , version 1

Citer

Stéphane Doncieux. Knowledge extraction from learning traces in continuous domains. AAAI 2014 fall Symposium ''Knowledge, Skill, and Behavior Transfer in Autonomous Robots''., 2014, Arlington, United States. pp.1-8. ⟨hal-02987425⟩
22 Consultations
43 Téléchargements

Partager

Gmail Facebook X LinkedIn More