Personally, I like the CRL foundations and formulations that are still under debate. For robotics applications, I personally think training pathologies could be a bottleneck, and good evaluation protocols and benchmarks are also essential for prototype studies before deployment.

Thanks for the question! I think the question itself should be an important topic in the workshop, and we aim to bring a broad range of diversity in speakers (including highly-regarded professors on robotics) and attendees. A list of topics is available on our website, which may give you some ideas.

RL in Big Worlds is a workshop at @rl-conference.bsky.social about ideas that enable agents to achieve goals in environments vastly more complex than themselves.

This requires giving agents the ability to learn continually and use approximate value functions, models, and policies effectively.

🔥Thrilled to announce the Continual Reinforcement Learning (CRL) Workshop @continual-rl.bsky.social @rl-conference.bsky.social 2026 in Montreal, Canada!

📣 We welcome submissions on broad topics of continual RL. Interested in submitting or reviewing? Check out our website for more details!