Bayesian Inference for Least Squares Temporal Difference Regularization

Nikolaos Tziortziotis 1 Christos Dimitrakakis 2, 3
2 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : This paper proposes a fully Bayesian approach for Least-Squares Temporal Differences (LSTD), resulting in fully probabilistic inference of value functions that avoids the overfitting commonly experienced with classical LSTD when the number of features is larger than the number of samples. Sparse Bayesian learning provides an elegant solution through the introduction of a prior over value function parameters. This gives us the advantages of probabilistic predictions, a sparse model, and good generalisation capabilities, as irrelevant parameters are marginalised out. The algorithm efficiently approximates the posterior distribution through variational inference. We demonstrate the ability of the algorithm in avoiding overfitting experimentally.
Type de document :
Communication dans un congrès
ECML 2017 - European Conference on Machine Learning, Sep 2017, Skopje, Macedonia
Liste complète des métadonnées

Littérature citée [34 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01593212
Contributeur : Christos Dimitrakakis <>
Soumis le : lundi 25 septembre 2017 - 20:44:04
Dernière modification le : mercredi 25 avril 2018 - 15:43:36
Document(s) archivé(s) le : mardi 26 décembre 2017 - 14:26:20

Fichier

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

Identifiants

  • HAL Id : hal-01593212, version 1

Citation

Nikolaos Tziortziotis, Christos Dimitrakakis. Bayesian Inference for Least Squares Temporal Difference Regularization. ECML 2017 - European Conference on Machine Learning, Sep 2017, Skopje, Macedonia. 〈hal-01593212〉

Partager

Métriques

Consultations de la notice

238

Téléchargements de fichiers

112