Learning States Representations in POMDP
By Gabriella Contardo, Ludovic Denoyer, Thierry Artières, Patrick Gallinari. 2013
7 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Reinforcement Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Niklas Wahlstrom
- Marc Peter Deisenroth
- Thomas Bo Schön
- Sergey Levine
- Pieter Abbeel
- Jan Peters
- Chelsea Finn
- Gerhard Neumann
In Reinforcement Learning
- Thomas Bo Schön
- Niklas Wahlstrom
- Marc Peter Deisenroth
- Sergey Levine
- Pieter Abbeel
- Jan Peters
- Gerhard Neumann
- Chelsea Finn
Citations in the corpus
- From Pixels to Torques: Policy Learning with Deep Dynamical Models (2015, background): “Moreover, Lange & Ried-miller (2010) presented an approach, which learns good discrete actions to control a slot car based on raw images, employing deep architectures for finding compact low-dimensional representations.”