28973 articles – 22398 Notices  [english version]

inria-00618037, version 1

Transfer from Multiple MDPs

Alessandro Lazaric () 1, Marcello Restelli a, 2

(2011)

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 into the training set used to solve a given 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.

  • a –  Politecnico di Milano
  • 1 :  SEQUEL (INRIA Lille - Nord Europe)
  • INRIA – CNRS : UMR8146 – Université Lille I - Sciences et technologies – Université Lille III - Sciences humaines et sociales – Ecole Centrale de Lille
  • 2 :  Departement of Electronics and Informatics
  • Politecnico di Milano
  • Domaine : Informatique/Intelligence artificielle
    Informatique/Apprentissage
  • Mots-clés : Reinforcement Learning – Transfer Learning
  • Versions disponibles :  v1 (31-08-2011) v2 (01-09-2011)
 
  • inria-00618037, version 1
  • http://hal.inria.fr/inria-00618037
  • oai:hal.inria.fr:inria-00618037
  • Contributeur : Alessandro Lazaric <>
  • Soumis le : Mercredi 31 Août 2011, 14:43:40
  • Dernière modification le : Mercredi 31 Août 2011, 14:46:22