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.
Poster De Conférence
Année : 2014
Lip6 Publications : Connectez-vous pour contacter le contributeur
https://hal.science/hal-01222594
Soumis le : vendredi 30 octobre 2015-11:31:59
Dernière modification le : mardi 11 avril 2023-15:16:28
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⟩
Collections
72
Consultations
0
Téléchargements