Near-Optimal BRL using Optimistic Local Transitions - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Near-Optimal BRL using Optimistic Local Transitions

Mauricio Araya-López
  • Fonction : Auteur
  • PersonId : 881106
Vincent Thomas
Olivier Buffet

Résumé

Model-based Bayesian Reinforcement Learning (BRL) allows a sound formalization of the problem of acting optimally while facing an unknown environment, i.e., avoiding the exploration-exploitation dilemma. However, algorithms explicitly addressing BRL suffer from such a combinatorial explosion that a large body of work relies on heuristic algorithms. This paper introduces bolt, a simple and (almost) deterministic heuristic algorithm for BRL which is optimistic about the transition function. We analyze bolt's sample complexity, and show that under certain parameters, the algorithm is near-optimal in the Bayesian sense with high probability. Then, experimental results highlight the key differences of this method compared to previous work.
Fichier principal
Vignette du fichier
icml12.pdf (270.19 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00755270 , version 1 (20-11-2012)

Identifiants

  • HAL Id : hal-00755270 , version 1

Citer

Mauricio Araya-López, Vincent Thomas, Olivier Buffet. Near-Optimal BRL using Optimistic Local Transitions. International Conference on Machine Learning - ICML 2012, Jun 2012, Edimburgh, United Kingdom. ⟨hal-00755270⟩
230 Consultations
89 Téléchargements

Partager

Gmail Facebook X LinkedIn More