🔊Simplicial Embeddings (SEMs) Improve Sample Efficiency in Actor-Critic Agents🔊

In our recent preprint we demonstrate that the use of well-structured representations (SEMs) can dramatically improve sample efficiency in RL agents.

1/X

This work was led by @johanobandoc.bsky.social and @waltermayor.bsky.social , with @lavoiems.bsky.social , Scott Fujimoto and Aaron Courville.

Read the paper at arxiv.org/abs/2510.13704

11/X

📢 ¡Buenas noticias!
Se extiende el período de inscripciones 🎉
No pierdas esta oportunidad de ser parte de un evento único que puede transformar tu futuro en la inteligencia artificial.
👉 Regístrate ahora y asegura tu lugar.
lasala.ai#top

Thrilled to share our #ICML2025 paper “The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep RL”, led by Jiashun Liu and with other great collaborators!

We teach RL agents when to quit wasting effort, boosting efficiency with our proposed method LEAST.

Here's the story 🧵👇🏾

proud to share a survey of state representation learning in RL that my student ayoub echchahed and i prepared, that was just published on
@tmlrorg.bsky.social !
this was the bulk of ayoub's masters thesis and he put a lot of work and care into it!
a few details in thread below...
1/

The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks

thrilled to share our #ICML2025 paper led by Walter Mayor & @johanobandoc.bsky.social , with Aaron Courville, where we explore how data collection affects agents in parallelized setups.
1/

really excited about this new work we just put out, led by my students @roger-creus.bsky.social & @johanobandoc.bsky.social , where we examine the challenges of gradient propagation when scaling deep RL nets.

roger & johan put in a lot of work and care in this work, check out more details in 🧵👇🏾 !

I'm excited to share a new paper: "Mastering Board Games by External and Internal Planning with Language Models"

storage.googleapis.com/deepmind-med...

(also soon to be up on Arxiv, once it's been processed there)

Everyone I spoke to at @rl-conference.bsky.social last summer agreed on it being one of the best conferences ever for an RL researcher... So many great RL-focused papers!
CFP is out, send your work here!

Post based on a talk I gave earlier this year at the AutoRL workshop in ICML, and leveraging two recent papers (1st with @joaogui1.bsky.social & @johanobandoc.bsky.social , 2nd with @jessefarebro.bsky.social ):

1-hparam transfer openreview.net/forum?id=szU...

2-CALE openreview.net/forum?id=vlU...

📢 In Defense Of Atari 📢

New blog post in which I argue why the ALE is still a valuable resource for RL research!

psc-g.github.io/posts/resear...

Good performance shouldn’t mean 'just in English' anymore 🪩

We provide a robust way to assess models with a new benchmark that captures in-language nuances and cultural contexts.

Last year I gave a talk titled "From 'Bigger, Better, Faster' to 'Smaller, Sparser, Stranger'", which looked at the components that make up our BBF agent (arxiv.org/abs/2305.19452), highlighting some promising areas of research.

Finally in blog form, have a read!
psc-g.github.io/posts/resear...

While I will be talking about some of our research work, there are also several fun and engaging features for fans to explore blog.google/technology/a... as well as a new Kaggle challenge on developing efficient Chess AI www.kaggle.com/competitions... under resource constraints.

A great new essay on AI for Science from our colleagues here:

deepmind.google/public-polic...

RLDM will be held next year in Dublin!

A reminder that the call for workshops is out: rldm.org/call-for-wor...

The workshops are one of my favourite parts of the conference :) please get in touch if you have any questions!