Automated RL

An RLC Workshop for Automated RL: Exploring Meta-Learning, Auto ML and LLMs

August 15, 2026

Montréal, Canada

About

In the past few years, we have seen a surge of interest in reinforcement learning, with breakthrough successes of applying RL in games, robotics, chemistry, logistics, nuclear fusion and more. These headlines, however, blur the picture of what remains a brittle technology, with successes relying on heavily engineered solutions!

In this workshop, we want to bring together different communities working on solving these problems. A variety of distinct sub-communities spanning RL, Meta-Learning and AutoML have been working on making RL work out-of-the-box in arbitrary settings - this is the AutoRL setting. Recently, LLMs and their in-context learning abilities, have significantly impacted all these communities. There are LLM agents tackling traditional RL tasks as well as few-shot RL agents increasing efficiency and generalization that are also trying to automate RL. LLMs have also been influencing AutoML directly with papers such as OptFormer. However, there is currently little crossover between these communities. As such, we create a space to connect them and shape the future of AutoRL.

This is a full-day workshop. The first half of the day features short talks tutorials from our speakers. Afterwards, we will host a podium discussion about the future directions of AutoRL. Using this panel as backdrop for the rest of the day, we open the floor to submitted work, which includes poster sessions and lightning talks. (See the detailed schedule.)

Call for Papers

Topics. We welcome submissions on topics including, but not limited to:

Hyperparameter optimisation for RL
Neural architecture design and search for RL
Automated reward design and shaping
Representation learning for RL
Normalisation and stabilisation techniques
Optimisation methods tailored to RL
Meta-learning in RL
Environment and curriculum design
Benchmarking and evaluation protocols
Reproducibility and robustness in RL
Bridging AutoML and RL methodologies
Practical deployment of RL systems
Use of large language models in RL and AutoRL

We particularly encourage work that connects multiple aspects of RL system design or proposes integrated automation approaches.

Formatting. There is a page limit of seven content pages (excluding the references, acknowledgements, and appendices). All submissions should be in the RLC format; see the submission guide for more details.

Dual Submissions. Work that is in submission or under review at a conference or journal is welcome. We are not accepting already-published work.