RL4AA'26

What is RL4AA'26?

We are pleased to announce RL4AA'26, the fourth workshop of the series organised by the Reinforcement Learning for Autonomous Accelerators (RL4AA) Collaboration. After three very successful workshops (KIT in 2023, Salzburg in 2024, and DESY in 2025) RL4AA'26 will be hosted as a LIV.INNO Workshop on Reinforcement Learning for Autonomous Accelerators by the University of Liverpool and Cockcroft Institute in the musically iconic port city of Liverpool.

RL4AA brings together the reinforcement learning and accelerator physics communities to share results, practical insights from the field, and the big questions ahead for real-world RL. Expect engaging keynotes, invited and contributed talks, a lively poster session, and a hands-on coding challenge.

Scope

Submissions are not limited to particle accelerators. We welcome any work on sequential decision-making in real-world settings (e.g., safety, sample efficiency, sim-to-real, partial observability). A set of student talk slots will be reserved.

Coding challenge

Join a team to tackle an accelerator-themed RL task. We will form balanced teams that mix newer folks and experienced contributors. You’ll submit results to a live Kaggle leaderboard as you go, improve your model, and we will wrap with awards for the top three teams

Who should attend

Whether you are deep into RL research or just starting and curious, there’s something for you (from introductory lectures the first day to advanced talks).

Registration

The event is free, but places are limited. Please register early to secure your spot.

We can’t wait to welcome you to Liverpool in 2026!

Keynote Speakers

We have a very exciting line-up of keynote speakers, and are very much looking forward to their talks!

Samuele Tosatto
Assistant Professor
University of Innsbruck

Abstract

Samuele Tosatto is an Assistant Professor at the University of Innsbruck, where he develops machine learning techniques for autonomous robot learning. Before his position in Innsbruck, Samuele earned his PhD at the Technical University of Darmstadt (Germany) under the supervision of Prof. Jan Peters, followed by a postdoctoral position at the Reinforcement Learning and Artificial Intelligence (RLAI) laboratory at the University of Alberta (Canada). Despite recent progress in the field, autonomous learning remains sample-inefficient and challenging to apply in the real world. Samuele's research is focused on making reinforcement learning more efficient by analyzing and revising its core components and developing techniques that embed assumptions that better capture the complexity of the physical world.