Yannis Flet-Berliac

Deep Reinforcement Learning Ph.D. student at SequeL

CNRS

I’m a Ph.D. student in Machine Learning at SequeL with strong interest in Deep Reinforcement Learning. I’m under the supervision of Philippe Preux.

Before starting my Ph.D., I graduated from DTU (machine learning, deep learning, social networks analysis) and École Centrale (advanced probabilities, software engineering, project management). I also worked as a ML Engineer at iAdvize for one year and for three different startups when I was in Denmark.

When the weather permits, I like to go out to run, cross-country ski, or windsurf. I also like to go out for more hygge activities whatever the weather.

Interests

Artificial Intelligence
Reinforcement Learning
Deep Learning
Making music & videos
Playing the piano
Fly some drone
Late musical evenings
Finish a bullet-point list

Education

Ph.D. in Machine Learning, now

SequeL, Inria, University of Lille, France
M.Sc. in Machine Learning, 2017

Technical University of Denmark, Denmark
M.Sc. in General Engineering, 2017

École Centrale de Nantes, France
Degree in Digital Business and IT, 2015

Audencia School of Management, France

Publications

Y. Flet-Berliac, P. Preux
Samples Are Useful? Not Always: denoising policy gradient updates using variance explained.
(Under Review) arXiv preprint arXiv:1904.04025, 2019.

Paper

Y. Flet-Berliac, P. Preux
High-Dimensional Control Using Generalized Auxiliary Tasks.
HAL preprint hal-02295705, 2019.

Paper

Y. Flet-Berliac, P. Preux
MERL: Multi-Head Reinforcement Learning.
Deep Reinforcement Learning Workshop, NeurIPS, 2019.

Paper

Y. Flet-Berliac
The Promise of Hierarchical Reinforcement Learning.
The Gradient, 2019.

Article

B. Johansen, Y. Flet-Berliac, M. Korzepa, P. Sandholm, N. Pontoppidan, M. Petersen, J. Larsen
Hearables in Hearing Care: Discovering Usage Patterns Through IoT Devices.
International Conference on Universal Access in Human-Computer Interaction, 2017.

Paper

Invited Talks

Oral & Panel Discussion: Do we control the algorithms we create?

November, 2019

Open Forum Art and Research

Improving Policy Gradient Updates with MERL and SAUNA

October, 2019

SequeL Inria Seminar

Deep Reinforcement Learning at Scale

April, 2019

The HPC-BigData Inria Project Lab (IPL)

QA and Deep Learning for Language Understanding

November, 2017

Machine Learning Meetup Nantes

Teacher Assistant

Reinforcement Learning - Fall 2019 - MVA - ENS Paris-Saclay

Instructors: Alessandro Lazaric, Matteo Pirotta & Reda Ouhamma

Reinforcement Learning Summer School 2019

Instructors: Felix Berkenkamp, Tristan Cazenave, Ludovic Denoyer, Gabriel Dulac-Arnold, Audrey Durand, Vincent François-Lavet, Matteo Hessel, Emilie Kaufmann, Marc Lanctot, Max Lapan, Alessandro Lazaric, Odalric-Ambrym Maillard, Jérémie Mary, Gerhard Neumann, Guillaume Obozinski, Olivier Pietquin, Bilal Piot, Matteo Pirotta, Bruno Scherrer, Florian Strub, Eleni Vasilaki, Oriol Vinyals