Use Beta NLL for regression when you also predict standard deviations, a simple change to NLL that works reliably better.

If open-endedness has to be fundamentally subjectively measured, what are the factors of the agent makes it so if we fix humans as the final arbiter or evaluator. Does embodiment/action space etc of the agent matter for a human evaluator of open-endedness?

🤣 generalrobots.substack.com/p/a-brief-in...

Tübingen: Freiburg:: Introvert:Extrovert

This might be the most fun I’ve had writing an essay in a while. Felt some of that old going-nuts-with-an-idea energy flowing. open.substack.com/pub/contrapt...

This week's #PaperILike is "Model Predictive Control and Reinforcement Learning: A Unified Framework Based on Dynamic Programming" (Bertsekas 2024). If you know 1 of {RL, controls} and want to understand the other, this is a good starting point. PDF: arxiv.org/abs/2406.00592

I realized how I background process tonnes of information, from work/research and emotional stuff. And it works well, leads to good research ideas, wise processing of tough situations! But It's so hard to learn to trust this as conscious thinking for solving problems feels more under my "control"

TIL: "Clever Hans cheat" for next-token prediction. A subtle but interesting issue with next-token prediction. In the purely forward next token prediction objective, teacher forcing can lead to learning dynamics where the models don't even generalize "in-distribution"!! arxiv.org/abs/2403.06963

Break the Monday Productivity ceiling with this super awesome 4 hour techno set on.soundcloud.com/hXTcWTTsYUNK...

Monday kick starter open.spotify.com/track/6QXjBA...

If I have a really good photo that could be potentially used in many contexts, what's the best place to make money with it? My friend has a really good eye for photos and we want to try a side venture selling some of her stuff

RIP Manmohan Singh. Dude changed all our lives in 1991 for the better. His stint as turnaround finance minister was revolutionary even if his later stint as PM was rather hapless (for which Nehru dynasty is more to blame).

Looks like a cool study. Lots to learn from ants about large scale coordination www.pnas.org/doi/10.1073/... "Our results exemplify how simple minds can easily enjoy scalability while complex brains require extensive communication to cooperate efficiently." h/t @petersuber.bsky.social

This album is going to be timeless open.spotify.com/album/32yQDx...

Wednesday Quirky mood open.spotify.com/track/3RBhQ7...

Does augmenting ourselves with V/LLMs to cognitive gaps make self actualization even more difficult on average? Stands stark in contrast with (more difficult/slower to show positive outcomr) augmentation strategies like meditation or psychedelics

The slides for my lectures on (Bayesian) Active Learning, Information Theory, and Uncertainty are online now 🥳 They cover quite a bit from basic information theory to some recent papers: blackhc.github.io/balitu/ and I'll try to add proper course notes over time 🤗

Manifold garden is a trippy game www.youtube.com/watch?v=vLt4...

Check out Motivo, a behavioral foundation model for humanoid control by FAIR. It's a one-of-its-kind unsupervised RL project, and it comes with a demo that is SO fun to play with! metamotivo.metademolab.com (for the record, they use compile and cudagraphs -> github.com/facebookrese...)

Modern life is a Turing tarpit: “Everything is possible, but nothing is easy” By contrast any traditional lifestyle is sub-Turing All the people pining for rituals, steady routines, deep work etc etc etc… YOU CAN’T HANDLE THE TURING COMPLETENESS en.wikipedia.org/wiki/Turing_...

If you're at NeurIPS, RLC is hosting an RL event from 8 till late at The Pearl on Dec. 11th. Join us, meet all the RL researchers, and spread the word!

One thing coding with LLMs has helped me a lot during the past months is for visualisations. I'm churning out code to visualize many aspects of agent behavior which I wouldn't have done before due to my mental friction in writing such code. Such code to do visualisations is also easy to verify.

When predicting discrete joint distribution of two variables with a neural network, what loss is the best to use? KL on the joint and two marginals? Or is there anything better?

In an effort to play a small part in creating additional value on this site, I'm going to post one-per-day a paper we wrote that was published in 2024. Together with memes. Skipping holidays/weekends. In random order. Would love your thoughts on them. I'll keep them threaded for easy finding! >

The RL book by Kevin Murphy is finally online (copied shamelessly from the other place) arxiv.org/abs/2412.05265

As an analogy, I also think we should prioritize decarbonizing electricity over making it renewable (e.g. I think we should use nuclear power for the foreseeable future). And the reason is simple: resources are finite, and climate change is the more pressing problem.

1/ You may have seen us talk about formaldehyde — a chemical that causes an inescapable cancer risk for everyone in America. It’s in the air we breathe. And it’s in our homes: our couches, our clothes, even babies’ cribs. So what can you do to reduce your exposure? THREAD 🧵

How much of the benefit of learning purely in simulations like Dreamer etc, comes from the fact that the shitty model at the start of the training somehow allows the agent to explore large parts of the state space efficiently?

An updated intro to reinforcement learning by Kevin Murphy: arxiv.org/abs/2412.05265! Like their books, it covers a lot and is quite up to date with modern approaches. It also is pretty unique in coverage, I don't think a lot of this is synthesized anywhere else yet

If you're in NeurIPS, you gotta meet Lennart! He's one of the friendliest folks who can describe a new concept to you in a must clear, & intuitive way, while also listening to your ideas with a similar intensity! Maybe your next nobel collaborator, you never know 😉

Excited to be at #NeurIPS2024 tomorrow! 🎉 Let’s connect if you are interested in tabular data and: 🤖 AutoML (e.g., AutoGluon) 📊 Data Science (e.g., LLMs for Feature Engineering) 🏛️ Foundation Models (e.g., TabPFN) Looking forward to insightful discussions—feel free to reach out!

DnB + code = Productive Monday open.spotify.com/track/1zfp3y...

I can't begin to describe how life-changing this new project, ShellSage, has been for me over the last few weeks. ShellSage is an LLM that lives in your terminal. It can see what directory you're in, what commands you've typed, what output you got, & your previous AI Q&A's.🧵

Excited to present "Latent Functional Maps" at #NeurIPS ! We show how neural models can be aligned by matching function spaces on representation manifolds, providing a unified framework for model comparison, matching, and information transfer. 📜: arxiv.org/abs/2406.14183 👇🧵

🚨 We just updated our perspective on representational alignment. The most recent version is both more crisp and more comprehensive. We try to find common language across research disciplines for aligning the representations from different info processing systems! arxiv.org/abs/2310.13018

Great blog post, just learnt about Mask Atari! arxiv.org/abs/2203.16777

Big news! The AutoML Conference is back! 🎉 Next year, we’re heading to the city that never sleeps: New York City🗽. Save the date: Sept 8–11, 2025. Stay tuned for updates, and in the meantime, check out our website: 2025.automl.cc. See you there? #AutoML25 #AutoMLConf #NYC #AutoML

My brain on coffee sounds exactly like this album open.spotify.com/album/0o8LTj...

Hear the gnomes and their Irreversible Echoes open.spotify.com/album/4Ei7fn...

Is this a rave/trippy album poster or is it a biology poster? Or both 🤣

This is impressive but also makes me wonder where Gen AI is going. Cane modeling things in the observation space lead to same level of interestingness as the source games or the real world? Can these model generate long tail events consistently compared to the real world/ human created games

Key arguments from the ICRA debate “Generative AI will make a lot of traditional robotics approaches obsolete” (1/6) A thread 🧵 Have to say, just like my own mind, both the parties eventually seemed pretty on the fence and waiting for time to decide on this one. www.roboticsdebates.org

Introducing 🧞Genie 2 🧞 - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents 🧠.

It has worked for text, images, and weather. Why not for power grids? Here's our perspective in Joule for a grid foundation model authors.elsevier.com/c/1kCag925JE... This large research effort will be Open Source, as the GridFM project hosted under Linux Foundation Energy!

📌 Thread of threads for research ideas 💡 Collaborations are most welcome 😁

The call for papers for RLC is now up! Abstract deadline of 2/14, submission deadline of 2/21! Please help us spread the word. rl-conference.cc/callforpaper...

How come I didn't know about this BeNeRL seminar series? It focuses on practical RL and seems really great! www.benerl.org/seminar-seri... I would have loved to hear Benjamin Eysenbach, Chris Lu and Edward Hu... Next one is on December 19th.

The deep goal of bluesky is to decentralize the social internet so that every individual controls their experience of it rather than having it be controlled by 5 random billionaires. Everyone thinks they signed up for a demuskified twitter...we actually signed an exciting and bizarre experiment.

Thrilled to share our NeurIPS spotlight on uncertainty disentanglement! ✨ We study how well existing methods disentangle different sources of uncertainty, like epistemic and aleatoric. While all tested methods fail at this task, there are promising avenues ahead. 🧵 👇 1/7 📖: arxiv.org/abs/2402.19460

Who is the best professor at managing their lab that you know?