RLVS 2021đź”—

Welcome to the 2021 Reinforcement Learning Virtual School's website.

This edition was hosted by the Toulouse AI institute ANITI, with the support of IRT Saint Exupéry, ISAE-SUPAERO, LAAS-CNRS, Université Fédérale Toulouse Midi-Pyrénées.

It was officially sponsored by DeepMind.

We also thank Institut de Mathématiques de Toulouse - Université Toulouse III - Paul Sabatier, Toulouse School of Economics - Université Toulouse I - Capitole.

This virtual event took place in March and April 2021. It gathered 1500 registered participants from 43 different countries. All recordings and class materials that the speakers gave us permission to share can be found on this website.

Goals of RLVSđź”—

RLVS intends to provide a high-quality, easy access to the field of Reinforcement Learning to new researchers. It aims to:
- Allow attendees to step in to the field of RL
- Learn from top lecturers in the field
- Provide broad access to live classes

We expect the participants to be a mixture of masters and Ph.D. students, academics, and industrial researchers with a solid background in mathematics and computer science.

RLVS scheduleđź”—

This condensed schedule does not include class breaks and social events. Times are Central European Summer Time (UTC+2).

March 25th 9:00-9:10 Opening remarks S. Gerchinovitz
9:10-9:30 RLVS Overview E. Rachelson
9:30-13:00 RL fundamentals E. Rachelson
14:00-16:00 Introduction to Deep Learning D. Wilson
16:30-17:30 Reward Processing Biases in Humans and RL Agents I. Rish
17:45-18:45 Introduction to Hierarchical Reinforcement Learning D. Precup
March 26th 10:00-12:00 Stochastic bandits T. Lattimore
14:00-16:00 Monte Carlo Tree Search T. Lattimore
16:30-17:30 Multi-armed bandits in clinical trials D. A. Berry
April 1st 9:00-15:00 Deep Q-Networks and its variants B. Piot, C. Tallec
15:15-16:15 Regularized MDPs M. Geist
16:30-17:30 Regret bounds of model-based reinforcement learning M. Wang
April 2nd 9:00-12:30 Policy Gradients and Actor Critic methods O. Sigaud
14:00-15:00 Pitfalls in Policy Gradient methods O. Sigaud
15:30-17:30 Exploration in Deep RL M. Pirotta
April 8th 9:00-11:00 Evolutionary Reinforcement Learning D. Wilson, J.-B. Mouret
11:30-12:30 Evolving Agents that Learn More Like Animals S. Risi
14:00-16:00 Micro-data Policy Search K. Chatzilygeroudis, J.-B. Mouret
16:30-17:30 Efficient Motor Skills Learning in Robotics D. Lee
April 9th 9:00-13:00 RL tips and tricks A. Raffin
14:30-15:30 Symbolic representations and reinforcement learning M. Garnelo
15:45-16:45 Leveraging model-learning for extreme generalization L. P. Kaelbling
17:00-17:30 RLVS wrap-up E. Rachelson, S. Gerchinovitz


Sorted alphabetically
Donald A. Berry University of Texas and Rice University
Konstantinos Chatzilygeroudis University of Patras
Marta Garnelo DeepMind
Matthieu Geist Google Brain
Leslie P. Kaelbling MIT
Tor Lattimore DeepMind
Dongheui Lee Technical University of Munich
Jean-Baptiste Mouret INRIA
Bilal Piot DeepMind
Matteo Pirotta Facebook AI Research
Doina Precup McGill University, DeepMind
Emmanuel Rachelson ISAE-SUPAERO, Université de Toulouse
Antonin Raffin DLR
Irina Rish Université de Montréal
Sebastian Risi University of Copenhagen
Olivier Sigaud Sorbonne Université
Corentin Tallec DeepMind
Mengdi Wang Princeton University
Dennis Wilson ISAE-SUPAERO, Université de Toulouse


Program committee
David Bertoin IRT Saint Exupéry
Tommaso Cesari Toulouse School of Economics
Sébastien Gerchinovitz IRT Saint Exupéry and Institut de Mathématiques de Toulouse
Nicolas Mansard LAAS-CNRS
Emmanuel Rachelson ISAE-SUPAERO, Université de Toulouse
Local arrangement chair
Corinne Joffre Université de Toulouse
Communication chair
Alix Fauque de Jonquières Université de Toulouse

Teaching assistantsđź”—

Photo Photo