Here at #EWRL: demonstration of autonomous tomato harvesting by polybot.eu #Robot #Harvesting #Learning

I wrote a short post on our newest ICML paper addressed at people who are not experts in machine learning. Check it out!

Should you be in the RL grad student / postdoc starter pack and aren't? This makes adding you much easier if you want to comment below

🚨AISTATS workshop proposals open! Big News: For the first time, there will be a day of workshops at #AISTATS 2026, in Tangier, Morocco 🌴🇲🇦 Quentin Berthet @qberthet.bsky.social and I are workshop chairs. virtual.aistats.org/Conferences/... Deadline: Oct 17, AOE

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!)

AISTATS CfP is out, and this year @qberthet.bsky.social and I are the first Workshop chairs! Call for Workshops to come very soon, but in short: aistats will have one more day dedicated to contributed workshops. Prepare your submissions!

We are excited to bring #EurIPS 2025 to Copenhagen in December. Consider becoming a sponsor and support us in making this inaugural event a success! Sponsorship packages are available and can be further customized if necessary. Reach out if you have any questions ❔ Info: eurips.cc/become-spons...

EWRL in Tübingen on Sept 17-19: Registrations are open!

hey wasn't this the same company that made a beautiful shiny "research" post about how AI evals should include error bars or something like that. or did they decide the CLT didn't apply here

EurIPS includes a call for both Workshops and Affinity Workshops! We look forward to making #EurIPS a diverse and inclusive event with you. The submission deadlines are August 22nd, AoE. More information at: eurips.cc/call-for-wor... eurips.cc/call-for-aff...

PSA: NeurIPS position track has no rebuttal period so reviews won’t be released until August. Don’t bother emailing the PCs! (Multiple people have asked me why their reviews aren’t visible. PCs should send a mass email and change the CFP.)

Everyone's talking about AI performance on the IMO. Let me highlight 🇨🇦Canadian 11th grader Warren Bei🇨🇦, one of five participants with a *perfect* 42/42. This is his *fifth* (and final) IMO representing Canada, with three golds and two silvers. (➡️ MIT undergrad in the fall)

Sergey Levine was just presenting in the Exploration in AI @ #ICML2025 and promoted that exploration needs to be grounded, and that VLMs are a good source ;-) Check our paper below 👇

Such an inspiring talk by @arkrause.bsky.social at #ICML today. The role of efficient exploration in Scientific discovery is fundamental and I really like how Andreas connects the dots with RL (theory).

I generally agree with the points made here. I am not sure what are the arguments from the neurips side, probably mainly the fear that the community would split. But right now it’s effectively split since so many people cannot travel to the US.

Hello #ICML2025👋, anyone up for a diffusion circle? We'll just sit down somewhere and talk shop. 🕒Join us at 3PM on Thursday July 17. We'll meet here (see photo, near the west building's west entrance), and venture out from there to find a good spot to sit. Tell your friends!

Onno and I will be presenting our poster at # W1005 tomorrow (Wed) morning. He made a great thread about it, come chat with us about POMDP theory :)

At #ICML, you can just use scholar inbox to help you find your way through the poster sessions. It just sorts the papers according to your preferences and it really works. www.scholar-inbox.com/conference/i... ICML 2025 Planner

Will be at ICML and looking to hire a postdoc to help us scale up and deploy RL in self-driving. So, hit me up to chat.

This is a question that deserves a blog post answer, but I'm going to do a quick response here. Gather around children as I tell you a story from ancient times. The year was 2015... at that point, it appeared that you needed Google scale to build competitive computer vision systems. 1/x

The only way I can navigate the ML literature these days is #ScholarInbox. At conferences, it builds a list of relevant posters for each session and I don’t know what I’d do without it. I 100% recommend this tool. www.scholar-inbox.com

🚨The ELLIS Fellow & Scholar nomination call is now open! 👏 ❗Please review the updated evaluation guidelines before submitting: https://bit.ly/4lmzRIN ℹ️ Instructions for submission and eligibility criteria: https://bit.ly/3HRdcWJ 🗓️ Submit by: Sept 30th, 2025

Help make RLC even more fun!

📣Join us at COLT 2025 in Lyon for a community event! 📅When: Mon, June 30 | 16:00 CET What: Fireside chat w/ Peter Bartlett & Vitaly Feldman on communicating a research agenda, followed by mentorship roundtable to practice elevator pitches & mingle w/ COLT community! let-all.com/colt25.html

Come hang out with us at COLT 2025 and think about crafting and communicating your research agenda!

So, looks like @seva.bsky.social has a ‘stack, and it’s excellent. Subscribe early, subscribe often! hegemon.substack.com/p/teaching-i...

It was a dream come true to teach the course I wish existed at the start of my PhD. We built up the algorithmic foundations of modern-day RL, imitation learning, and RLHF, going deeper than the usual "grab bag of tricks". All 25 lectures + 150 pages of notes are now public!

Works that use #VAML/ #MuZero losses often use deterministic models. But if we want to use stochastic models to measure uncertainty or because we want to leverage current SOTA models such as #transformers and #diffusion, we need to take care! Naively translating the loss functions leads to mistakes!

Give @pedanana.bsky.social a follow everybody (and put her on some RL lists!) She was our longest running undergrad intern, showed incredible dedication on the hardest and most frustrating projects, and is now starting her grad school career with the amazing Martha White (who is not on Bluesky?!)

Great talk by @claireve.bsky.social about our joint work on memory traces this morning. Come join me at poster 94 if you want to know more! #RLDM2025

This morning at #RLDM I talked about Memory Traces, a simple representation for POMDPs that’s probably good at remembering old observations. arxiv.org/abs/2503.15200

Eau de Q-Network: a smart transformation of a Landscape poster into a Portrait format, and also cool NN distillation for Deep RL. #RLDM

Wild cool stuff going on at RLDM in Dublin this week!

Join us for Nneka's presentation tomorrow! Last talk before the summer break.

Accepted papers for #COLT2025 learningtheory.org/colt2025/acc...

Hey folks, if anyone's interested, there are still a few hours to submit your papers for Royal Stat Society's event on innovative usages of natural experimewnts: rss.org.uk/news-publica... #CausalSky #StatSky

📣 Although the paper submission deadline has passed, there's still time to submit a contributed talk! Are you an early-career researchers? We invite you to submit a talk proposal for EWRL 2025. 🎤 Accepted speakers will be given a 15-minute presentation slot at the workshop.

Your personalized CVPR 25 @cvprconference.bsky.social conference programs are now available for you! www.scholar-inbox.com/conference/c...

Great talks make complicated things so clear they seem easy. This was such a talk: youtu.be/nCR8hWgvwTI?...

Our work on Open Loop RL will be presented by @onnoeberhard.com at L4DC this week. He made a very nice summary thread ⬇️

I'm flying to Michigan today to present our new paper "A Pontryagin Perspective on Reinforcement Learning" at L4DC, where it has been nominated for the Best Paper Award! We ask the question: is it possible to learn an open-loop controller via RL? 🧵

If you are at L4DC, my talk will be on Thursday at 9:45, and the poster is #3.2. Please come by! Joint work with @claireve.bsky.social and Michael Muehlebach.

If you're finishing your camera-ready for ACL or ICML and want to cite co-first authors more fairly, I just made a simple fix to do this! Just add $^*$ to the authors' names in your bibtex, and the citations should change :) github.com/tpimentelms/...

🎤 Meet the speakers! Peter Dayan (www.mpg.de/12309370/bio...) is Director of the MPI for Biological Cybernetics and a pioneer in neuroscience and AI. His work focuses on brain decision-making, the role of neuromodulators and neuronal malfunctions in psychiatric diseases . 🕙 Still time to submit!

So happy with the @rl-conference.bsky.social accepted paper list: openreview.net/group?id=rl-... So much stuff that feels worth reading, going to try to spotlight one a day

Thoughtful and nuanced post on the role of LLMs in reviewing and how we can think about it as a research community.

Early registrations are ending soon for RLC, get your tickets before May 30th and join us in Alberta this summer!

Request for research: cool results coming out of GDM from @pcastr.bsky.social and friends on the interplay between NN training phenomena and RL such as plasticity loss and bottlenecks. Unfortunately, mostly in Atari: 1) a bit expensive 2) unclear if transfers to other envs arxiv.org/abs/2505.17749

Dhruv Rohatgi will be giving a lecture on our recent work on comp-stat tradeoffs in next-token prediction at the RL Theory virtual seminar series (rl-theory.bsky.social) tomorrow at 2pm EST! Should be a fun talk---come check it out!!

Quite the insightful post about the use of LLMs in peer-review. Since that ship has left the stable, let's understand and mitigate the possible adverse effects. bryanwilder.github.io/files/llmrev... E.g., "scientists should demand that any system used as part of peer review be openly accessible"