Finite-Sample Analysis of LSTD - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Finite-Sample Analysis of LSTD

Alessandro Lazaric
Mohammad Ghavamzadeh
  • Fonction : Auteur
  • PersonId : 868946
Remi Munos
  • Fonction : Auteur
  • PersonId : 836863

Résumé

In this paper we consider the problem of policy evaluation in reinforcement learning, i.e., learning the value function of a fixed policy, using the least-squares temporal-difference (LSTD) learning algorithm. We report a finite-sample analysis of LSTD. We first derive a bound on the performance of the LSTD solution evaluated at the states generated by the Markov chain and used by the algorithm to learn an estimate of the value function. This result is general in the sense that no assumption is made on the existence of a stationary distribution for the Markov chain. We then derive generalization bounds in the case when the Markov chain possesses a stationary distribution and is $\beta$-mixing.

Domaines

Informatique
Fichier principal
Vignette du fichier
lstd-tech.pdf (303.36 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

inria-00482189 , version 1 (09-05-2010)

Identifiants

  • HAL Id : inria-00482189 , version 1

Citer

Alessandro Lazaric, Mohammad Ghavamzadeh, Remi Munos. Finite-Sample Analysis of LSTD. ICML - 27th International Conference on Machine Learning, Jun 2010, Haifa, Israel. pp.615-622. ⟨inria-00482189⟩
496 Consultations
473 Téléchargements

Partager

Gmail Facebook X LinkedIn More