LSTD with Random Projections - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

LSTD with Random Projections

Résumé

We consider the problem of reinforcement learning in high-dimensional spaces when the number of features is bigger than the number of samples. In particular, we study the least-squares temporal difference (LSTD) learning algorithm when a space of low dimension is generated with a random projection from a high-dimensional space. We provide a thorough theoretical analysis of the LSTD with random projections and derive performance bounds for the resulting algorithm. We also show how the error of LSTD with random projections is propagated through the iterations of a policy iteration algorithm and provide a performance bound for the resulting least-squares policy iteration (LSPI) algorithm.
Fichier non déposé

Dates et versions

hal-00943120 , version 1 (07-02-2014)

Identifiants

  • HAL Id : hal-00943120 , version 1

Citer

Mohammad Ghavamzadeh, Alessandro Lazaric, Odalric Maillard, Rémi Munos. LSTD with Random Projections. Advances in Neural Information Processing Systems, 2010, Granada, Spain. ⟨hal-00943120⟩
89 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More