Bayesian Reinforcement Learning

Nikos Vlassis 1 Mohammad Ghavamzadeh 2 Shie Mannor 3 Pascal Poupart 4
2 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
Abstract : This chapter surveys recent lines of work that use Bayesian techniques for reinforcement learning. In Bayesian learning, uncertainty is expressed by a prior distribution over unknown parameters and learning is achieved by computing a posterior distribution based on the data observed. Hence, Bayesian reinforcement learning distinguishes itself from other forms of reinforcement learning by explicitly maintaining a distribution over various quantities such as the parameters of the model, the value function, the policy or its gradient. This yields several benefits: a) domain knowledge can be naturally encoded in the prior distribution to speed up learning; b) the exploration/exploitation tradeoff can be naturally optimized; and c) notions of risk can be naturally taken into account to obtain robust policies.
Type de document :
Chapitre d'ouvrage
Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State of the Art, Springer Verlag, 2012
Liste complète des métadonnées

https://hal.inria.fr/hal-00840479
Contributeur : Mohammad Ghavamzadeh <>
Soumis le : mardi 2 juillet 2013 - 15:31:33
Dernière modification le : jeudi 11 janvier 2018 - 06:22:13
Document(s) archivé(s) le : jeudi 3 octobre 2013 - 10:45:23

Fichier

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

Identifiants

  • HAL Id : hal-00840479, version 1

Collections

Citation

Nikos Vlassis, Mohammad Ghavamzadeh, Shie Mannor, Pascal Poupart. Bayesian Reinforcement Learning. Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State of the Art, Springer Verlag, 2012. 〈hal-00840479〉

Partager

Métriques

Consultations de la notice

608

Téléchargements de fichiers

1837