Transfer from Multiple MDPs - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

Transfer from Multiple MDPs

Résumé

Transfer reinforcement learning (RL) methods leverage on the experience collected on a set of source tasks to speed-up RL algorithms. A simple and effective approach is to transfer samples from source tasks and include them in the training set used to solve a target task. In this paper, we investigate the theoretical properties of this transfer method and we introduce novel algorithms adapting the transfer process on the basis of the similarity between source and target tasks. Finally, we report illustrative experimental results in a continuous chain problem.
Fichier principal
Vignette du fichier
sourcetransfer.pdf (307.52 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00772620 , version 1 (10-01-2013)

Identifiants

  • HAL Id : hal-00772620 , version 1

Citer

Alessandro Lazaric, Marcello Restelli. Transfer from Multiple MDPs. NIPS - Twenty-Fifth Annual Conference on Neural Information Processing Systems, Dec 2011, Granada, Spain. ⟨hal-00772620⟩
196 Consultations
93 Téléchargements

Partager

Gmail Facebook X LinkedIn More