Could we meta-learn which data to train on? Yes!
Does this make LLM training more efficient? Yes!
Would you like to know exactly how? arxiv.org/pdf/2505.17895

(come see us at NeurIPS too!)

Where do some of Reinforcement Learning's great thinkers stand today?

Find out! Keynotes of the RL Conference are online:
www.youtube.com/playlist?lis...

Wanting vs liking, Agent factories, Theoretical limit of LLMs, Pluralist value, RL teachers, Knowledge flywheels
(guess who talked about which!)

On my way to #ICML2025 to present our algorithm that strongly scales with inference compute, in both performance and sample diversity! 🚀

Reach out if you’d like to chat more!

Deadline to apply is this Wednesday!

Ever thought of joining DeepMind's RL team? We're recruiting for a research engineering role in London:
job-boards.greenhouse.io/deepmind/job...
Please spread the word!

When faced with a challenge (like debugging) it helps to think back to examples of how you've overcome challenges in the past. Same for LLMs!

The method we introduce in this paper is efficient because examples are chosen for their complementarity, leading to much steeper inference-time scaling! 🧪

Some extra motivation for those of you in RLC deadline mode: our line-up of keynote speakers -- as all accepted papers get a talk, they may attend yours!

@rl-conference.bsky.social

200 great visualisations: 200 facets and nuances of 1 planetary story.

Reposting David Silver's talk about how RL is the way to intelligence. No particular reason
www.youtube.com/watch?v=pkpJ...

Excited to announce the first RLC 2025 keynote speaker, a researcher who needs little introduction, whose textbook we've all read, and who keeps pushing the frontier on RL with human-level sample efficiency

Could language games (and playing many of them) be the renewable energy that Ilya was hinting at yesterday? They do address two core challenges of self-improvement -- let's discuss!

My talk is today at 11:40am, West Meeting Room 220-222, #NeurIPS2024
language-gamification.github.io/schedule/

Don't get to talk enough about RL during #neurips2024? Then join us for more, tomorrow night at The Pearl!

This year's (first-ever) RL conference was a breath of fresh air! And now that it's established, the next edition is likely to be even better: Consider sending your best and most original RL work there, and then join us in Edmonton next summer!

Are there limits to what you can learn in a closed system? Do we need human feedback in training? Is scale all we need? Should we play language games? What even is "recursive self-improvement"?

Thoughts about this and more here:
arxiv.org/abs/2411.16905

RLC will be held at the Univ. of Alberta, Edmonton, in 2025. I'm happy to say that we now have the conference's website out: rl-conference.cc/index.html

Looking forward to seeing you all there!

@rl-conference.bsky.social
#reinforcementlearning

Twitter-optional NeurIPS? Sounds like an appealing prospect!