Léonard Blier

According to our database, Léonard Blier authored at least 7 papers between 2018 and 2022.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2022

Sur certaines méthodes raisonnées pour l'apprentissage par renforcement profond. (Some Principled Methods for Deep Reinforcement Learning).

Léonard Blier

PhD thesis, 2022

2021

Unbiased Methods for Multi-Goal Reinforcement Learning.

Léonard Blier, Yann Ollivier

CoRR, 2021

Learning Successor States and Goal-Dependent Values: A Mathematical Viewpoint.

Léonard Blier, Corentin Tallec, Yann Ollivier

CoRR, 2021

2019

Learning with Random Learning Rates.

Léonard Blier, Pierre Wolinski, Yann Ollivier

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2019

Making Deep Q-learning methods robust to time discretization.

Corentin Tallec, Léonard Blier, Yann Ollivier

Proceedings of the 36th International Conference on Machine Learning, 2019

2018

Do Deep Learning Models Have Too Many Parameters? An Information Theory Viewpoint.

Léonard Blier, Yann Ollivier

CoRR, 2018

The Description Length of Deep Learning models.

Léonard Blier, Yann Ollivier

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018