Incremental Basis Function Expansion in Reinforcement Learning using Cascade-Correlation Networks

Sertan Girgin 1 Philippe Preux 1, 2
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
Abstract : In machine learning, in parallel to algorithms themselves, the representation of data is a point of utmost importance. Efforts on data pre-processing in general are a key ingredient to success. An algorithm that performs poorly on a particular form of given data may perform much better, both in terms of efficiency and the quality of the solution, when the same data is represented in another form. Despite the amount of literature on the subject, the issue of how to enrich a representation to suit the underlying mechanism is clearly still pending. In this paper, we approach this problem within the context of reinforcement learning, and in particular, interested in discovery of a ''good'' representation of data for the LSPI algorithm. To this end, we use the cascade-correlation learning architecture to automatically generate a set of basis functions which would lead to a better approximation of the value function, and consequently improve the performance of the resulting policies. We also show the effectiveness of the idea on some benchmark problems.
Type de document :
Rapport
[Research Report] RR-6505, INRIA. 2008
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00272368
Contributeur : Sertan Girgin <>
Soumis le : lundi 21 avril 2008 - 16:04:20
Dernière modification le : jeudi 11 janvier 2018 - 06:22:13
Document(s) archivé(s) le : vendredi 25 novembre 2016 - 22:58:57

Fichiers

inria.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00272368, version 2

Collections

Citation

Sertan Girgin, Philippe Preux. Incremental Basis Function Expansion in Reinforcement Learning using Cascade-Correlation Networks. [Research Report] RR-6505, INRIA. 2008. 〈inria-00272368v2〉

Partager

Métriques

Consultations de la notice

253

Téléchargements de fichiers

401