Lightnews — Scholar-powered news

Reposted by Antonin Raffin

prefix.dev @prefix.dev · 2h

In our little deep dive series we're now exploring how cross-compilation in the Conda ecosystem works: prefix.dev/blog/cross-c.... Back in the days, @conda-forge.org rolled this out widely to support osx-arm64 early on, and now for linux-aarch64/ppc64le.

Cross compiling in the Conda ecosystem

Cross compiling is a fundamental capability in modern software development, allowing developers to build packages for different architectures without needing access to the target hardware.

prefix.dev

4 3

Reposted by Antonin Raffin

Daphne Cornelisse @daphne-cornelisse.bsky.social · 1d

Rapid RL experimentation is great. But how do you catch silent errors before they slip by?

In this post, I share tools and habits that help me move quickly from idea to result without sacrificing reliability.

How to catch subtle RL bugs before they catch you

Tools and habits for reliable, fast RL experimentation and development

open.substack.com

5 39

Reposted by Antonin Raffin

Grant Sanderson @3blue1brown.com · 2d

Ever since I made a video about Fourier Transforms, one of the most requested topics on the channel has been its close cousin, the Laplace Transform.

I've been having a lot of fun animating a mini-series about this topic, and the main part is now out.

youtu.be/j0wJBEZdwLs

But what is a Laplace Transform?

YouTube video by 3Blue1Brown

youtu.be

9 66 400

Reposted by Antonin Raffin

Sebastian Raschka (rasbt) @sebastianraschka.com · 4d

Updated & turned my Big LLM Architecture Comparison article into a video lecture.

The 11 LLM archs covered in this video:
1. DeepSeek V3/R1
2. OLMo 2
3. Gemma 3
4. Mistral Small 3.1
5. Llama 4
6. Qwen3
7. SmolLM3
8. Kimi 2
9. GPT-OSS
10. Grok 2.5
11. GLM-4.5/4.6

www.youtube.com/watch?v=rNlU...

The Big LLM Architecture Comparison

YouTube video by Sebastian Raschka

www.youtube.com

9 51

Antonin Raffin @araffin.bsky.social · 4d

Mjlab

Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research.

github.com/mujocolab/mj...

GitHub - mujocolab/mjlab: Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research.

Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research. - mujocolab/mjlab

github.com

1 2 7

Antonin Raffin @araffin.bsky.social · 15d

SBX (SB3 Jax) v0.23.0 is out =)!

I added CNN support for PPO.
It turns out that using a shared features extractor (CNN in this case) is important for achieving good performance on Atari games.

Perf report: wandb.ai/openrlbenchm...

github.com/araffin/sbx

GitHub - araffin/sbx: SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms

SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms - araffin/sbx

github.com

1 7

Antonin Raffin @araffin.bsky.social · 16d

Training a small humanoid robot with reinforcement learning using another robot for reset.

by Kaizhe Hu et al. (ToddlerBot Stanford)

Project page: robot-trains-robot.github.io

a robot arm support a robot humanoid on a treadmill

1 6

Antonin Raffin @araffin.bsky.social · 18d

Open-Source Hardware in the Era of Robot Learning Workshop @ CoRL 2025

Website: open-hardware-robots.github.io/CoRL2025/

2 15

Reposted by Antonin Raffin

Stéphane Caron @locoscaron.fosstodon.org.ap.brid.gy · 18d

The CoRL 2025 workshop on Open-Source Hardware in the Era of Robot Learning is starting now! You can join the conversation online via live streaming: https://www.youtube.com/live/ZVPIJzF1df4

1 1

Reposted by Antonin Raffin

sophie-xhonneux.bsky.social @sophie-xhonneux.bsky.social · 23d

📣 Call for Blog Posts at #ICLR2026 @iclr_conf

Following the success of the past iterations, we are opening the Call for Blog Posts 2026!

iclr-blogposts.github.io/2026/about/#...

Please retweet!

abs-0.twimg.com

1 8 13

Antonin Raffin @araffin.bsky.social · 23d

A practical introduction to (deep) RL, providing intuitions to understand the more recent algorithms.

The plan is to start from tabular Q-learning and work our way up to Deep Q-learning (DQN). In a following post, I will continue on to Soft Actor-Critic (SAC) and its extensions.

Antonin Raffin @araffin.bsky.social · 26d

RL102: From Tabular Q-Learning to Deep Q-Learning (DQN) - A Practical Introduction to (Deep) Reinforcement Learning

araffin.github.io/post/rl102/

RL102: From Tabular Q-Learning to Deep Q-Learning (DQN) | Antonin Raffin | Homepage

This blog post is meant to be a practical introduction to (deep) reinforcement learning1, presenting the main concepts and providing intuitions to understand the more recent Deep RL algorithms. For a ...

araffin.github.io

18

Reposted by Antonin Raffin

Stéphane Caron @locoscaron.fosstodon.org.ap.brid.gy · 23d

Next Saturday, 𝗔𝗻𝘁𝗼𝗶𝗻𝗲 𝗣𝗶𝗿𝗿𝗼𝗻𝗲 will present Pollen Robotics & Hugging Face's open-source robots, including Reachy Mini, the SO-100 arm, the Amazing Hand and the Open Duck Mini. He will discuss the sim2real challenges of making the Open Duck Mini walk, and how […]

[Original post on fosstodon.org]

The Open Duck Mini open-source and open-hardware robot.

1 6

Antonin Raffin @araffin.bsky.social · 26d

Code and colab notebooks: github.com/araffin/rlss...

GitHub - araffin/rlss23-dqn-tutorial: Deep Q-Network (DQN) and Fitted Q-Iteration (FQI) tutorial for RL Summer School 2023

Deep Q-Network (DQN) and Fitted Q-Iteration (FQI) tutorial for RL Summer School 2023 - araffin/rlss23-dqn-tutorial

github.com

4

Antonin Raffin @araffin.bsky.social · 26d

RL102: From Tabular Q-Learning to Deep Q-Learning (DQN) - A Practical Introduction to (Deep) Reinforcement Learning

araffin.github.io/post/rl102/

RL102: From Tabular Q-Learning to Deep Q-Learning (DQN) | Antonin Raffin | Homepage

This blog post is meant to be a practical introduction to (deep) reinforcement learning1, presenting the main concepts and providing intuitions to understand the more recent Deep RL algorithms. For a ...

araffin.github.io

1 2 13

Reposted by Antonin Raffin

prefix.dev @prefix.dev · Sep 5

Package building with Pixi is being rolled out! Dive into our latest blog post on crafting C++ packages.

And guess what? It’s not just for C++; Pixi plays nice with Python, Rust, ROS, Mojo, and beyond!

prefix.dev/blog/pixi-b...

Build C++ projects with Pixi

Painless dependency management (including shared libraries), monorepos and CI/CD is here for C++/CMake projects with Pixi.

prefix.dev

1 3 15

Reposted by Antonin Raffin

Julia's Reruns Bot @b0rk-reruns.jvns.ca · Sep 3

bash tricks

permalink: wizardzines.com/comics/bash-...
from our zine "Bite Size Command Line": wizardzines.com/zines/bite-s...

A comic about computing. A transcript may be available at the link in the post.

5 19

Reposted by Antonin Raffin

Michiel van de Panne @mvandepanne.bsky.social · Sep 3

This is absolutely true -- this is a superb and much-needed consolidation of so much of modern RL. Kevin, inquiring minds want to understand the process you use to put this artwork together! @sirbayes.bsky.social Perhaps this is also the ultimate benchmark for Gemini Deep Research reports. ;-p

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · Sep 3

Reminded again of Kevin Murphy's excellent RL overview: arxiv.org/abs/2412.05265
A lot of the stuff covered here really is at the cutting edge and not compiled so nicely anywhere else

Reinforcement Learning: An Overview

This manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement learning and sequential decision making, covering value-based methods, policy-based methods, model-based m...

arxiv.org

1 10

Reposted by Antonin Raffin

Red Blob Games @redblobgames.com · Sep 1

Weekend project: building a (site) search engine www.redblobgames.com/blog/2025-08... just for fun! :)

Let’s write a search engine, part 1 of 2

www.redblobgames.com

4 28

Reposted by Antonin Raffin

Zeynep Akata @zeynepakata.bsky.social · Aug 28

NeurIPS has decided to do what ICLR did: As a SAC I received the message 👇 This is wrong! If the review process cannot handle so many papers, the conference needs yo split instead of arbitrarily rejecting 400 papers.

8 17 110

Reposted by Antonin Raffin

Tom Schaul @schaul.bsky.social · Aug 27

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!)

1 23 75

Antonin Raffin @araffin.bsky.social · Aug 19

How astronauts control robots from space

(featuring our quadruped Bert 👀)

youtu.be/BMFPVCu16SQ

How astronauts control robots from space

YouTube video by European Space Agency, ESA

youtu.be

2

Reposted by Antonin Raffin

James MacGlashan @jmac-ai.bsky.social · Aug 15

This one's been a long time coming.

In this post on Decisions & Dragons I answer "Should we abandon RL?"

The answer is obviously no, but people ask because they have a fundamental misunderstanding of what RL is.

RL is a problem, not an approach.

www.decisionsanddragons.com/posts/should...

4 11 44

Reposted by Antonin Raffin

EWRL18 @ewrl18.bsky.social · Aug 13

📣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!

PheedLoop

PheedLoop: Hybrid, In-Person & Virtual Event Software

site.pheedloop.com

4 8

Reposted by Antonin Raffin

Ben Recht @beenwrekt.bsky.social · Aug 13

If machine learning is a game, it’s Calvinball. Bitter lessons from chess don’t apply.

All our games turn into Calvinball

Why lessons from chess don't apply to machine learning

www.argmin.net

3 20

Reposted by Antonin Raffin

Stéphane Caron @locoscaron.fosstodon.org.ap.brid.gy · Aug 12

Join us for the 𝗖𝗼𝗥𝗟 𝟮𝟬𝟮𝟱 𝘄𝗼𝗿𝗸𝘀𝗵𝗼𝗽 𝗼𝗻 𝗢𝗽𝗲𝗻-𝗦𝗼𝘂𝗿𝗰𝗲 𝗛𝗮𝗿𝗱𝘄𝗮𝗿𝗲 𝗶𝗻 𝘁𝗵𝗲 𝗘𝗿𝗮 𝗼𝗳 𝗥𝗼𝗯𝗼𝘁 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴! The day will bring together researchers and makers from both academia and the industry to discuss open-source robot design, integration with reinforcement learning […]

[Original post on fosstodon.org]

Flyer for the workshop on Open-Source Hardware in the Era of Robot Learning taking place at CoRL 2025

1 3