Learning States Representations in POMDP - Archive ouverte HAL Accéder directement au contenu
Poster De Conférence Année : 2014

Learning States Representations in POMDP

Résumé

We propose to deal with sequential processes where only partial observations are available by learning a latent representation space on which policies may be accurately learned.

Dates et versions

hal-01222594 , version 1 (30-10-2015)

Identifiants

Citer

Gabriella Contardo, Ludovic Denoyer, Thierry Artières, Patrick Gallinari. Learning States Representations in POMDP. International Conference on Learning Representations, ICLR 2014, Apr 2014, Banff, Canada. 2014. ⟨hal-01222594⟩
53 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More