Sabitlenmiş Tweet
الله في أُمةٍ، جار الزمان بها .. يفنى الزمان ولا يفنى لها ألمُ!
— إيليا أبو ماضي
العربية
Bilal Hammoud
660 posts
@abhi9u This book does an amazing job at teaching it
arxiv.org/abs/2403.14606
English
I've been looking into autograd internals of Pytorch.
While I was aware of how backward mode autodiff works, I didn't know there was also forward mode autodiff. I had to read up on that. There is a very comprehensive article from an MIT course on that, I highly recommend it.
English
Bilal Hammoud retweetledi
Bilal Hammoud retweetledi
Atlas can perform a backflip combo like a gymnast and also walk naturally across a stage.
These very different movements are enabled by the whole-body learning framework developed by the RAI Institute and deployed by @BostonDynamics. We’re getting closer to robust, generalist humanoid behaviors that transfer zero-shot from simulation to physical performance: bit.ly/4rcbMYv
English
Bilal Hammoud retweetledi
Bilal Hammoud retweetledi
Reinforcement learning is used to speed the production of behavior for the @BostonDynamics Atlas humanoid robot. At the heart of the learning process is a physics-based simulator that generates training data for a variety of maneuvers.
English
Glad to have been a part of this for the past two years :) stay tuned for more exciting progress in the future 🚴♂️🚴♂️🚴♂️
RAI Institute@rai_inst
In this demo, Ultra Mobile Vehicle (UMV) drives, turns, jumps, tricks, and comes to a sudden stop called a track-stand. All of the driving, landings, balance, and track-stands are done using reinforcement learning.
English
@Yuki_Doradora @ludo_righetti Thank you! Looking forward to seeing you this summer in Boston :)
English
very honored and lucky to have had @ludo_righetti as a phd advisor, thank you for everything !!
English
@machines_motion @bilalhammoud @loiannog Yay @bilalhammoud! And an extra yay for ending up in Boston!!
English