Reinforcement Learning Conference (RLC) was added to the AI conference DL countdown. rl-conference.cc March 1: Abstract DL (AoE) March 5: Submission DL (AoE) Conference: Montreal, Quebec, Canada, August 16th -19th, 2026.

good morning youtube www.youtube.com/watch?v=nJiH...

unexpectedly found a fascinating book nashpy.readthedocs.io/en/stable/te...

Noam's Brown twitter post about vibecoding of a Poker bot (might be relevant for code generation world models, see @sharky6000.bsky.social pinned post) The code actually looks OK github.com/noambrown/po... It has good educational value (to me, for example)

another very cool idea by the Paradigms of intelligence team: arxiv.org/abs/2512.20605 Control the agent not through its raw actions, but steer them in the controllable space of temporal abstractions. Good with time, due to its linear order -> sequential modelling. Neat.

a funny bit ngl

New paper for the Theory of Mind for AI workshop at AAAI Conference for Artificial Intelligence I propose that ToM mechanisms are used not only for social cognition, but also for calibrating the dimensionality of motor exploration in cumulatively cultural skill acquisition arxiv.org/abs/2601.01599

this is every person, basically many are unsure of impact they can make, some haven't got much mental resistance there were times, when I tried to convince people that they can do it. quite unsuccessful. unfortunately, it's essential how the person was brought up and who they're influenced by.

Let's start the year 2026 with some positive notes ❤️😂❤️😂

been recently playing with torch.complie and jax.jit, slightly different approaches to compilation but fun

I am sorry for posting this, but everytime I see opinions like this and, moreover, people I respect a lot retweeting them

it's not obvious how not to overcomplicate complexity of an abstraction doesn't really imply that one is better on the other hand, simplicity doesn't always lead to any meaningful progress unsupervised environment design.

je ce partegerai alors je me souviendrai ça et serai plus responsible. en tout cas, je crois ça.

welcome to 2026, gucci gang

today, I debugged a big chunk of code and hyperparameters (I can't do search thereof) with Gemini (free). the incentive is here, the model tends to "think" in a right direction, however, me and it more ran in circles than did actual stuff knowing that, I'm not sure that I want to spend money on AI

What if you could train agents on a 𝗱𝗲𝗰𝗮𝗱𝗲 of driving experience in 𝘂𝗻𝗱𝗲𝗿 𝗮𝗻 𝗵𝗼𝘂𝗿, on a single GPU? Excited to share 𝙋𝙪𝙛𝙛𝙚𝙧𝘿𝙧𝙞𝙫𝙚 2.0: A fast, friendly driving simulator with RL training via PufferLib at 𝟯𝟬𝟬𝗞 𝘀𝘁𝗲𝗽𝘀/𝘀𝗲𝗰 🐡 + 🚗 youtu.be/LfQ324R-cbE?...

I am not much into the prompt attacks for LLMs, however, this paper has a nice formalism to descritbe that "Attacker LLM" arxiv.org/abs/2512.20806

Reacting

an argmin year in review

Chimera: State Space Models Beyond Sequences Aakash Lahoti, Tanya Marwah, Ratish Puduppully, Albert Gu Action editor: Hankook Lee https://openreview.net/forum?id=yv0TUssepk #embeddings #imagenet #attention

add your own papers! wanted to say that the year was excellent, a lot of positive steps into llm-based mas and improved convergence for imperfect info games however, too much of adaptation too little of exploration looking forward to 2026

Yue Lin, Shuhui Zhu, Wenhao Li, Ang Li, Dan Qiao, Pascal Poupart, Hongyuan Zha, Baoxiang Wang Policy-Conditioned Policies for Multi-Agent Task Solving https://arxiv.org/abs/2512.21024

cool

Multi-agent review of the year? Bluesky exclusive!

slightly less iconic and maybe a bit flatter than Pendulum themselves, but still an excellent UK DnB from Metrik soft and energising at the same time www.youtube.com/watch?v=tL5E... maybe good for a cardio sesh, @sharky6000.bsky.social

cool channel and videos www.youtube.com/watch?v=4ac1...

My colleague Sanjay Ghemawat & I have done a fair bit of performance tuning of various pieces of code. We wrote an internal Performance Hints document ~2 years ago as a way of identifying some general principles & we've recently published a version of it externally. Doc: abseil.io/fast/hints.h...

still consider this paper an underrated banger btw there was a couple of talks about it one of them is www.youtube.com/watch?v=UKY0...

🌍 Planet Wars: RTS AI Competition → simonlucas.github.io/planet-wars-... 🏃 LoRR: League of Robot Runners → Website coming soon! 📅 Mark your calendars and start preparing!

Democratisation of AI research like that, making complicated things available to everyone — that is sweet. Do you use standard or batched variant of MCTS, though?

Whether you're into robotics, multi-agent systems, or strategic AI, there's a challenge waiting for you: ⚓ MCTF: The Third International Maritime Capture the Flag Competition → www.mctf26.com 📊 NSGYM: Evaluating Decision Agents under Non-Stationarity → nsgym.io/aamas2026_co...

gimme snow

cooperative foundation summer school lectures are live www.youtube.com/watch?v=e0oi... Seeing some fascinating ones

whoa

Unlike board games, real-world strategic interactions are messy. Traditional game theory thus needs a boost for the age of agentic AI. Our #AAMAS2026 workshop "Strategic Engineering"(sites.google.com/view/se-aama...) in Cyprus aims to bridge the gap. Come join us to unlock truly strategic AI!

Published here: cyprusconferences.org/aamas2026/wo...

WW research.google/blog/gemini-...

why blogs.nvidia.com/blog/nvidia-...

An earlier book I co-authored is on procedural content generation for games, the area of game AI that I have done the most research in. It's from 2016, but there's lots of useful stuff in there if you're into PCG: www.pcgbook.com

If you want to read recent work from my lab, see our reasonably updated web site: game.engineering.nyu.edu There's also my woefully out of date personal website: julian.togelius.com Perhaps more useful is a chronological sort of my Google Scholar profile: scholar.google.com/citations?hl...

If you want to really dig in, here's Georgios Yannakakis' and my textbook on Artificial Intelligence and Games - you can buy it from Springer, or just download it from our website (first edition, and draft of upcoming second edition): gameaibook.org It's long (especially 2nd edition) and technical.

If you want a very accessible intro (I wrote it so my parents could read it) intro to AI and games, here's my earlier book from 2019: mitpress.mit.edu/978026203903...

In "Thresholds of Digital Gameplay," Daniel Gardner demonstrates how a series of interfaces and other elements on the edges of gameplay are more central to gaming than we realize. Available #OpenAccess: mitpress.mit.edu/978026255358...

multiagent systems expertise (RL/generative agents) 😩😩😩😩 apply though

O_o

would like a gpu or a tpu

This is pretty cool! 👍 google-deepmind.github.io/disco_rl/

sad

british moosic music.youtube.com/watch?v=wfRc...

D2 Actor Critic: Diffusion Actor Meets Distributional Critic Lunjun Zhang, Shuo Han, Hanrui Lyu, Bradly C. Stadie Action editor: Manuel Haussmann https://openreview.net/forum?id=8KbstCUXhH #reinforcement #critic #behavioral