Come see our poster tomorrow morning (#4307 in Hall A)! Paper, code, and more can be found at onnoeberhard.com/q-commit. Joint work with @claireve.bsky.social and Michael Muhelebach.

Onno Eberhard@onnoeberhard.com · last mo.

I am in Seoul at ICML to present our newest paper "Commit to the Bit: Reactive Reinforcement Learning Done Right". We show that finding reactive policies in POMDPs is easier than previously thought and that the ubiquitous 𝑞⋆-realizability assumption is stronger than necessary. 🧵

I am in Seoul at ICML to present our newest paper "Commit to the Bit: Reactive Reinforcement Learning Done Right". We show that finding reactive policies in POMDPs is easier than previously thought and that the ubiquitous 𝑞⋆-realizability assumption is stronger than necessary. 🧵

Excited that our paper is finally out in @natneuro.nature.com 🎉 Huge thanks to all my co-authors, especially @jonasterlau.bsky.social & @randolph-helfrich.bsky.social for the support and great teamwork 🍀

Randolph Helfrich@randolph-helfrich.bsky.social · 3mo ago

Very excited to share our latest paper led by @nbinish.bsky.social in @natneuro.nature.com We demonstrate how a communication subspace channels higher-dimensional PFC dynamics into lower-D motor activity to enable efficient behavior using human iEEG. www.nature.com/articles/s41... #neuroskyence

Very excited to share our latest paper led by @nbinish.bsky.social in @natneuro.nature.com We demonstrate how a communication subspace channels higher-dimensional PFC dynamics into lower-D motor activity to enable efficient behavior using human iEEG. www.nature.com/articles/s41... #neuroskyence

A communication subspace relays context-dependent actions from human prefrontal to motor cortex - Nature Neuroscience

Context-dependent behavior selects actions according to task demands. Using direct brain recordings in humans, Binish et al. uncover how coordinated population activity efficiently channels informatio...

nature.com

The deadline for all SIGBOVIK 2026 papers has officially been extended to March 18! Enjoy the extra procrastination time, and maybe consider starting to write your papers!

Exciting workshop for RL enthusiasts in Mannheim! 👇 Workshop on Reinforcement Learning 2026, taking place on 𝐅𝐞𝐛𝐫𝐮𝐚𝐫𝐲 𝟔, 𝟐𝟎𝟐𝟔, at the 𝐔𝐧𝐢𝐯𝐞𝐫𝐬𝐢𝐭𝐲 𝐨𝐟 𝐌𝐚𝐧𝐧𝐡𝐞𝐢𝐦, Germany. Participation in the workshop is 𝐟𝐫𝐞𝐞 𝐨𝐟 𝐜𝐡𝐚𝐫𝐠𝐞! Check the program and register: www.wim.uni-mannheim.de/doering/conf...

Nicolo Cesa-Bianchi and Matteo Papini are putting together a great unconference workshop at the @ellis.eu day at @euripsconf.bsky.social If you want to talk about RL, causality, bandits, online learning, join us there on December 2nd sites.google.com/view/ilir-wo...

ILIR Workshop, Dec 2, 2025

This workshop covers current research topics in reinforcement learning and causality, and in particular questions at the interface of these research areas. Of particular interest this year are also qu...

sites.google.com

I had such a great time helping organize EWRL 2025 with an amazing team 🎉 Loved being part of it and meeting so many passionate reinforcement learning enthusiasts! @ewrl18.bsky.social

Truly chuffed for our fearless food physicists @mpipks.bsky.social + collabs from AT @istaresearch.bsky.social, IT & ES who won this year’s Ig Nobel - the #NobelPrize of hearts❤️for cracking the science of perfect pasta !🍝Kudos to all for intrepidly consuming lots of cheese in the name of science!😋

The Secret to a Smooth Pasta Sauce Wins Ig Nobel Prize

Italian researchers studied how the ingredients of the traditional Roman dish cacio e pepe emulsify into a creamy sauce, winning the 2025 Physics Ig Nobel Prize.

the-scientist.com

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

AIhub.org@aihub.org · 11mo ago

In our latest blog post, @onnoeberhard.com writes about work presented at #ICML2025 on partially observable reinforcement learning which introduces an alternative memory framework - “memory traces”. aihub.org/2025/09/12/m...

A cute little animation: a critically damped harmonic oscillator becomes unstable with integral control if the gain is too high. Here, at K_i = 2, a Hopf bifurcation occurs: two poles of the transfer function enter the right-hand s-plane and the closed-loop system becomes unstable.

📣Registration for EWRL is now open📣 Register now 👇 and join us in Tübingen for 3 days (17th-19th September) full of inspiring talks, posters and many social activities to push the boundaries of the RL community!

I am going to present the poster during the next poster session. 11am Wed. Poster W #707

Cansu Sancaktar@cansusancaktar.bsky.social · last yr.

✨Introducing SENSEI✨ We bring semantically meaningful exploration to model-based RL using VLMs. With intrinsic rewards for novel yet useful behaviors, SENSEI showcases strong exploration in MiniHack, Pokémon Red & Robodesk. Accepted at ICML 2025🎉 Joint work with @cgumbsch.bsky.social 🧵

I really, really like this paper and as an open question, would love to see it tested on more memory benchmarks

Onno Eberhard@onnoeberhard.com · last yr.

I am in Vancouver at ICML, and tomorrow I will present our newest paper "Partially Observable Reinforcement Learning with Memory Traces". We argue that eligibility traces are more effective than sliding windows as a memory mechanism for RL in POMDPs. 🧵

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 :)

Onno Eberhard@onnoeberhard.com · last yr.

I am in Vancouver at ICML, and tomorrow I will present our newest paper "Partially Observable Reinforcement Learning with Memory Traces". We argue that eligibility traces are more effective than sliding windows as a memory mechanism for RL in POMDPs. 🧵

I am in Vancouver at ICML, and tomorrow I will present our newest paper "Partially Observable Reinforcement Learning with Memory Traces". We argue that eligibility traces are more effective than sliding windows as a memory mechanism for RL in POMDPs. 🧵

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 is a joint work with @onnoeberhard.com and Michael Mühlebach, and the poster will be presented by Onno tonight at #RLDM, and later in July at @icmlconf.bsky.social

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

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

Onno Eberhard@onnoeberhard.com · last yr.

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? 🧵

Super interesting work, take a look! 👀

Onno Eberhard@onnoeberhard.com · last yr.

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? 🧵

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? 🧵

🎤 Meet the speakers! Marcus Hutter (www.hutter1.net) is a Senior Researcher at DeepMind and Honorary Professor at ANU. His research focuses on the information-theoretic foundations of inductive reasoning and reinforcement learning. ⌛Still time to submit your paper or contributed talk proposal!

🎤 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!

📢 Deadline extended! Submit your work to EWRL — now accepting papers until June 3rd AoE. This year, we're also offering a fast track for papers accepted at other conferences ⚡ Check the website for all the details: euro-workshop-on-reinforcement-learning.github.io/ewrl18/

News!⚡ We’re pleased to announce a new Call for Contributed Talks to bring novel and diverse viewpoints to EWRL2025. Early-career researchers are especially encouraged to submit proposals and share their work with the community. Full details: euro-workshop-on-reinforcement-learning.github.io/ewrl18/

Still a few days left to submit! ⌛ Don’t miss out! Check the website for all the details: euro-workshop-on-reinforcement-learning.github.io/ewrl18/

EWRL has been my favorite conference experience so far. Very excited that we are organizing it in Tübingen this year!

EWRL@ewrl-org.bsky.social · last yr.

Mark your calendars, EWRL is coming to Tübingen! 📅 When? September 17-19, 2025. More news to come soon, stay tuned!

Mark your calendars, EWRL is coming to Tübingen! 📅 When? September 17-19, 2025. More news to come soon, stay tuned!

Truly inspiring work.

James Gardner@jadgardner.bsky.social · last yr.

Are you tired of context-switching between coding models in @pytorch.org and paper writing on @overleaf.com? Well, I’ve got the fix for you, Neuralatex! An ML library written in pure Latex! neuralatex.com To appear in Sigbovik (subject to rigorous review process)