This workshop is mainly inspired by the "Big World" hypothesis.
In short, an RL agent in a big world can only sense a small part of its environment, and it is surrounded by other equally complex agents!
openreview.net/pdf?id=Sv7Da...
The organizing team is composed of @alexlewandowski.bsky.social, Carlo D'Eramo, Esraa Elelimy, @khurramjaved.com, @kris.pengy.ca, @theo-vincent.bsky.social, @jan-peters.bsky.social, and Richard Sutton
The call for papers is open!
Check it out: rlinbigworlds.ca/call_for_pap...
Submission deadline: 15 May 2026
If you are interested in reviewing, you can register here: forms.gle/YYfo96vxfMQv...
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.