We often hear about the theory-practice gap. At this workshop we will take a thorough look at this. Is there a gap? What is the nature of the gap? Who made it? Is it good to have the gap? If not, how to close it? I think this is super important for the healthiness of the field!

And there it comes. Our beloved child, OFUL is gone, it's in the past. RIP OFUL, hello new tail bound however you came to existence and whoever your parents are! :)

What is even "agnostic reinforcement learning" you may ask. Ok, that is easy: Find best policy in a given policy class. Come to talk to learn what we know about this problem.

Now that the #COLT2024 decisions are out, I'd like to announce a workshop that we are organize that will happen just before COLT. The workshop theme is RL Theory. All are welcome! Details here: rltheory-workshop.github.io Please spread the word!

Proud of you Amir-massoud Farahmand ! Well deserved!

And because there’s never enough RL Theory, if you have cool work on RL and/or Control Theory, check out our ICML workshop rl-control-theory.github.io Submissions open until May 27th for short or long papers (no proceedings)

I really enjoyed working on this paper. What's in here?We are making progress on making GP inference/sampling better scale with data, in particular, figuring out how to use SGD to make this happen. In short, conditioning, multiplicative vs. additive noise are key.

I know lot's of people could be busy with NeurIPS papers, but this talk looks too interesting too miss. I hope to see many of you there!

Love this work Kory Mathewson! Can't wait to see the creativity tools like this unlock!

If you are wrapping up your #NeurIPS2024 submission on #RL theory and/or Control theory, consider submitting to our ICML workshop rl-control-theory.github.io Deadline on May 27th :) Please repost 🙏

Also, it is not too late to register yet. Early registration deadline is June 14, in a week! Link: eventbrite.com/e/colt-2024-37…

Last reminder that the "early bird" ticket sales for #COLT2024 ends tomorrow, on June 14! Shipra Agrawal and Aaron Roth put together an awesome program. See learningtheory.org/colt2024/sched… Please repost for visibility. Hope to see you in Edmonton!

Now that RL_Conference is over (and what a success it was!), it's time to start thinking about the next one. If you haven't heard yet, RLC is going north. We'll be organizing RLC'25 in Edmonton! I'm very excited about that and look forward to seeing everyone there.

I don't really get into politics, but academic boycotts make no sense regardless of who is being targeted. If we compromise on keeping academics as free as possible of politics, soon we will be where the former "communist" countries were which produced a backwards system.

📢RL job alert!📢 martha and adam white are world-class experts in RL, and just fantastic people overall. if you're looking to work on real, challenging, and high-impact problems using RL, apply to work with them! rlcore.ai

Ready to push the boundaries of AI with your interdisciplinary research? Apply for a tenure-track role at one of Canada's largest centres for fundamental AI research! Learn more about these Amii and University of Alberta postings now: hubs.la/Q02Lkc2N0 #MLJobs #AIResearch #MLResearch

The new International Olympiad in AI (for high schoolers) is looking for nominations to the scientific committee. Important and impactful role, helping to shape what material/topics/problems talented teenagers first encounter in the topic. Reach out if you’d consider contributing

yes, what fun! kudos to the organizers!