European Workshop on Reinforcement Learning

October 2026

WARNING

The venue is not available today due to student protests. Please do not come, we will send a visio link shortly. Please look at https://ewrl2026.zulipchat.com/ for further informations.

Please attend from the zoom link available on the zulip and by email.

Tuesday news

We found a plan B for what is perhaps the most important part of EWRL : the poster sessions.

The computer science lab building, called ESPRIT, conveniently located next to the metro station “4 Cantons” (one stop after Cité Scientifique) is not blocked by students, and safe. The direction is here.

You are welcome to join us for a lunch cocktail at ESPRIT from 12.30pm.

We will then have the following program

1.30pm-3pm : Poster session C

3pm-3.30pm : Coffee break

3.30pm-5pm : Poster session D

The cocktail in the evening is canceled.

In the meantime we are looking for an alternative venue for tomorrow, we will keep you posted.

Here is also an update schedule for the Zoom session this morning :

Updated program for the Zoom session

9h15 Anders Jonsson Efficiency and Optimality of Hierarchical Reinforcement Learning

10h15 Lukas Zierahn et al. Best Arm Identification for Bandits with Shifting Means 10h30 Victor Villin et al. Inferring Transferable Rewards via Active Inverse Reinforcement Learning

10H45 Pablo Moreno Munoz et al. Generative Modeling by Value-Driven Transport

11H Florian Wolf et al. Global Optimality for Constrained Exploration via Penalty Regularization

11h15 Nathan Grinsztajn The industrialization of reinforcement learning

Wednesday news

For tomorrow we found a new conference venue that is not a University building. We will gather here, in a hotel called Ascotel (7 avenue Paul Langevin).

You can reach it from either the “Cité Scientifique” or “4 Cantons” metro stops.

The first talk starts at 9am and the schedule is the same as planned. For the poster session we will move to the ESPRIT building as we are today and then go back to Ascotel for lunch and the rest of the afternoon.

For the contributed talks, please upload your slides beforehand in the link given in the zulip (pdf format prefered).

The business meeting is moved to tomorrow at 1:15pm, in the amphitheatre.

19th European Workshop on Reinforcement Learning (EWRL 2026)

Description

The European Workshop on Reinforcement Learning (EWRL) is the gathering hub of the Reinforcement Learning research community in Europe and one of the main world-class events in RL. We plan to make the 2026 edition an exciting event for researchers worldwide, both for the presentation of top quality papers, but also as a forum for ample discussion of open problems and future research directions.

Past editions of EWRL can be found here.

Topics

Reinforcement learning is an active field of research which deals with the problem of sequential decision making in unknown (and often) stochastic and/or partially observable environments. Recently there has been a wealth of impressive empirical results, including those coupling Deep Learning function approximators with Reinforcement Learning algorithms, as well as significant theoretical advances. Both types of advances are of major importance and we aim to create a forum to discuss such interesting results, their applications, consequences, and research perspectives.

We encourage submissions in both theoretical and practical aspects of Reinforcement Learning.

Venue

EWRL 19 will be located in the University of Lille, France. It will take place in the LILLIAD learning center, the scientific university library. It is easily accessible from the city center and the train stations by taking the subway. Simply get on line 1, direction "4 cantons", and get off at "Cité scientifique professeur Gabillard". Look for the big round building: you're there!

Registration

Registrations are closed.

Key dates
Registration fees

Accomodation

It is easy to find a hotel in Lille using websites such as https://fr.hotels.com/ or booking.com, in particular in the city center which is 15 min metro away from the conference venue. But there are also two hotels on the campus. See our recommendations here. We also made a local guide explaining local transports and conference locations here.

Social

There are two social events.

Cocktail

The Cocktail will be held at Lilliad, the conference venue, on the 6th, from 6:00 pm to 8:00 pm.

No registration is required, and there's no need to leave the conference venue!

Gala Dinner

The Gala Dinner will be held at the Palais de la Bourse (40 Place du Théâtre), a landmark building dating from the early 20th century that was originally designed to house the Chamber of Commerce. Registration is mandatory (you will be able to opt in for the Gala Dinner during the workshop registration). There is no dress code for the gala dinner, come as you are!

We look forward to welcoming you there from 7:00pm onwards on Monday the 5th!

The venue is within walking distance of Lille Flandres railway station and Rihour metro station (https://maps.app.goo.gl/B7NVDReqjaaPrLzY9).

Keynote Speakers

Christian Duriez
DEFROST, Inria, Univ Lille, CNRS, Ecole Centrale de Lille, Compliance Robotics, France
Christian Duriez is a research director at Inria Lille, France, where he leads the DEFROST team. He earned his Ph.D. in Robotics from the CEA and Université d’Évry in 2004, followed by a postdoctoral position at CIMIT SimGroup in Boston, USA. His research focuses on interactive simulation of deformable objects, haptic rendering, and surgical simulation, with a strong emphasis on soft robotics modeling and control, fast finite element methods, and contact response simulation. A key contributor to the open-source SOFA framework, he co-founded InSimo (2013) and Compliance Robotics (2024), where he advances the use of soft robots for educational and industrial applications, particularly in the food industry.
Nathan Grinsztajn
Mistral.
Nathan Grinsztajn works on agents at Mistral AI. Previously, he was a Member of Technical Staff at Cohere, where he worked on RL for LLMs and reasoning, and before that a research scientist at InstaDeep, where he focused on transformers for combinatorial optimization and discrete problems.
Anders Jonsson
Universitat Pompeu Fabra.
Anders Jonsson is a full professor in the Department of Engineering, where he heads the Artificial Intelligence and Machine Learning research group. His research interests involve sequential decision problems in which one or several agents have to make repeated decisions about what to do, mainly in the form of automated planning and reinforcement learning.
Sao Mai Nguyen
Ensta-Paris.
Sao Mai Nguyen is an associate professor at Ensta-Paris. She is interested in robotics, artificial intelligence and cognitive science. She tries to bridge these 3 aspects in her work, and started working in cognitive developmental robotics. She has a special interest in linking research of machine learning, robotic embodiment, child development psychology and neuroscience.
Alexandre Proutiere
KTH, Royal Institute of Technology.
Alexandre Proutiere is a professor at the Decision and Control Systems division in the EECS school at KTH, Royal Institute of Technology. His research interests are Machine Learning and AI, reinforcement learning, unsupervised learning, statistics, stochastic processes, control; applications to communication and social networks, cybersecurity.
Giorgia Ramponi
University of Zurich.
Giorgia is an Assistant Professor with Tenure Track at the Faculty of Business, Economics, and Informatics at the University of Zurich. She is also an affiliated professor at the ETH AI Center and an affiliated professor at the Data Science and AI, Computer Science, and Engineering department at Chalmers University of Technology.
Pierre Schegg
CAMIN, Inria, LIRMM, Univ Montpellier, Montpellier, France
Pierre Schegg is a Post-Doc at Inria, University. He works on controlling soft robots in particular for use in medical applications such as Cardiology and Bariatric Surgery.
Aviv Tamar
Technion ECE.
Aviv Tamar is an associate professor at Technion ECE, where he heads the Robot Learning Lab. His research focuses on AI and machine learning, with an emphasis on robotics applications. His long term goal is to bring robots into human-centered domains such as homes and hospitals.

Organizers

Emilie Kaufmann
Organization Commitee
Université de Lille, CNRS
Rémy Degenne
Organization Commitee
Université de Lille, Inria
Timothée Mathieu
Organization Commitee
Université de Lille, Inria
Adrienne Tuynman
Organization Commitee
Université de Lille, Inria
Hector Kohler
Organization Commitee
Laboratoire d'Informatique de l'École Polytechnique
Thomas Michel
Organization Commitee
Université de Lille, Inria
Adrien Prevost
Organization Commitee
Université de Lille, Inria
Juliette Achddou
Organization Commitee
Université de Lille
Philippe Preux
Organization Commitee
Université de Lille
Udvas Das
Organization Commitee
Université de Lille, Inria
Odalric-Ambrym Maillard
Organization Commitee
Université de Lille, Inria
Debabrota Basu
Organization Commitee
Université de Lille, Inria
Julien Teigny
Organization Commitee
Inria
Yann Berthelot
Organization Commitee
Université de Lille, Inria
Brahim Driss
Organization Commitee
Université de Lille, Inria
Amélie Supervielle
Organization Commitee
Inria

Sponsors