Optimistic planning for belief-augmented Markov decision processes - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Optimistic planning for belief-augmented Markov decision processes

Lucian Busoniu
  • Fonction : Auteur
  • PersonId : 933138
Rémi Munos
  • Fonction : Auteur
  • PersonId : 836863

Résumé

This paper presents the Bayesian Optimistic Planning (BOP) algorithm, a novel model-based Bayesian reinforcement learning approach. BOP extends the planning approach of the Optimistic Planning for Markov Decision Processes (OP-MDP) algorithm [10], [9] to contexts where the transition model of the MDP is initially unknown and progressively learned through interactions within the environment. The knowledge about the unknown MDP is represented with a probability distribution over all possible transition models using Dirichlet distributions, and the BOP algorithm plans in the belief-augmented state space constructed by concatenating the original state vector with the current posterior distribution over transition models. We show that BOP becomes Bayesian optimal when the budget parameter increases to infinity. Preliminary empirical validations show promising performance.
Fichier principal
Vignette du fichier
adprl.pdf (464.82 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00840202 , version 1 (01-07-2013)

Identifiants

  • HAL Id : hal-00840202 , version 1

Citer

Raphael Fonteneau, Lucian Busoniu, Rémi Munos. Optimistic planning for belief-augmented Markov decision processes. IEEE International Symposium on Adaptive Dynamic Programming and reinforcement Learning, ADPRL 2013, Apr 2013, Singapour, Singapore. pp.CDROM. ⟨hal-00840202⟩
307 Consultations
255 Téléchargements

Partager

Gmail Facebook X LinkedIn More