Why am I working on RL for LLMs, when... I can go work on RL for Olaf... #humanoidssummitshow more

Does off-policy value-based RL scale? In LLMs, larger scale... predictably improves performance. Value-based RL learns from arbitrary data and is sample-efficient, but folk wisdom says it doesn't scale 🧵⬇️We show predictability for scaling value-based RL!show more

Y’all slept on this g!rl 🤦 Na one wh!te... guy bag am, see as the guy is happy, he won a jackpot 😆 The only 9ja curvy g!rl i know on SM that is smart, intelligent & hardworking! Congratulations to them 🥰💯show more

i can not wait to see his black hair... in rl 😩show more

Excited to share CrystalReasoner, a reasoning model for crystal... structure generation with LLMs and property-conditioned generation through RL: Website: Paper: Code:show more

Some part of our ongoing work on the news... :). Just sprinkled some RL into itshow more

I've gotten a mujoco sim RL training loop for... a unitree robot at 200k SPS. I'm looking into the physics for friction, contact dynamics. My goal: can I reproduce & beat the mujoco playground RL baselines This is running in my web browser with raylib. Its the baselineshow more

1/ While most RL methods use shallow MLPs (~2–5... layers), we show that scaling up to 1000-layers for contrastive RL (CRL) can significantly boost performance, ranging from doubling performance to 50x on a diverse suite of robotic tasks. Webpage+Paper+Code:show more

Mullin: There’s a lot of work we can do... to get DHS working for the American people…I am excited.show more

Thanks AK! Finally, robot can do continuous, agile, autonomous,... adaptive jumping over stair and stepping stone Key idea: combine the pros of model-free RL and model-based control. RL (for CoM refs) + QP (for GRF) + WBC (for torque) Open-sourced:show more

I am looking for this job, I can work... and pressure and long hours, I am a Christian.show more

These are not CGI. Reinforcement learning is so back.... When operating on strings, it gives us o3. When operating on physical motors, it gives us a perfect humanoid backflip and a robot creature that out-maneuvers almost every animal on earth. RL is one of the only learning algorithms that can master both the world of bits and the world of atoms. Give me a reward function, and I shall move the world. 2025, Year of RL.show more

A few selects of Animation / Motion Design work... for Moon back when I was working on the channel Made in After Effectsshow more

i am on the right path and everything will... work out for meshow more

I agree. That’s why we’ve been working on something... for this… dropping v soonshow more

🐶 there's only a month left for me to... go live for you guys, so i'm thinking of going live as many, as quick as i can. and while i'm doing my service, i prepared ahead some fun and good things that you can watch so i am working hard on preparing thoseshow more

Hmm what am I working on?!

"Why am i just seeing me and Bae on... my (for you page)" 😭show more