HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Theses

Recurrent Neural Networks and Reinforcement Learning: Dynamic Approaches

Corentin Tallec 1, 2
1 TAU - TAckling the Underspecified
LRI - Laboratoire de Recherche en Informatique, Inria Saclay - Ile de France
Abstract : An intelligent agent immerged in its environment must be able to both understand and interact with the world. Understanding the environment requires processing sequences of sensorial inputs. Interacting with the environment typically involves issuing actions, and adapting those actions to strive towards a given goal, or to maximize a notion of reward. This view of a two parts agent-environment interaction motivates the two parts of this thesis: recurrent neural networks are powerful tools to make sense of complex and diverse sequences of inputs, such as those resulting from an agent-environment interaction; reinforcement learning is the field of choice to direct the behavior of an agent towards a goal. This thesis aim is to provide theoretical and practical insights in those two domains. In the field of recurrent networks, this thesis contribution is twofold: we introduce two new, theoretically grounded and scalable learning algorithms that can be used online. Besides, we advance understanding of gated recurrent networks, by examining their invariance properties. In the field of reinforcement learning, our main contribution is to provide guidelines to design time discretization robust algorithms. All these contributions are theoretically grounded, and backed up by experimental results.
Document type :
Theses
Complete list of metadata

Cited literature [100 references]  Display  Hide  Download

https://hal.inria.fr/tel-02434367
Contributor : Marc Schoenauer Connect in order to contact the contributor
Submitted on : Friday, January 10, 2020 - 8:25:53 AM
Last modification on : Friday, February 4, 2022 - 3:13:59 AM
Long-term archiving on: : Saturday, April 11, 2020 - 2:50:16 PM

File

thesis_core.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : tel-02434367, version 1

Citation

Corentin Tallec. Recurrent Neural Networks and Reinforcement Learning: Dynamic Approaches. Artificial Intelligence [cs.AI]. Université Paris-Saclay, 2019. English. ⟨NNT : 2019SACLS360⟩. ⟨tel-02434367⟩

Share

Metrics

Record views

272

Files downloads

78