Saket
banner
tisaket.bsky.social
Saket
@tisaket.bsky.social
PhDing in DRL at Brown.
Reposted by Saket
Pretty cool results from Boston Dynamics using motion capture suit and trained using RL. The question is how well do the motions generalize to unseen behavior?
March 20, 2025 at 11:15 PM
Pretty cool results from Boston Dynamics using motion capture suit and trained using RL. The question is how well do the motions generalize to unseen behavior?
March 20, 2025 at 11:15 PM
hanumakinds latest banger is probably the best thing to start your week with

www.youtube.com/watch?v=MbJ7...
Hanumankind - Run It Up ( Prod. By Kalmi ) | (Official Music Video)
YouTube video by HanumankindVEVO
www.youtube.com
March 11, 2025 at 1:42 AM
Reposted by Saket
Barto and Sutton receive the Turing award!

Amazing recognition for two kind, pioneering, and genuinely inspiring scientists. Congratulations!!

awards.acm.org/about/2024-t...
Andrew Barto and Richard Sutton are the recipients of the 2024 ACM A.M. Turing Award for developing the conceptual and algorithmic foundations of reinforcement learning.
Andrew Barto and Richard Sutton as the recipients of the 2024 ACM A.M. Turing Award for developing the conceptual and algorithmic foundations of reinforcement learning. In a series of papers beginning...
awards.acm.org
March 5, 2025 at 12:31 PM
Reposted by Saket
Latest Turing Award winners again warn of AI dangers
Latest Turing Award winners again warn of AI dangers
A pattern is emerging here.
buff.ly
March 5, 2025 at 12:58 PM
Seeing Andrew Barto at RLC last year was one of my favorite moments. Overjoyed to see him get the turing award (long overdue).
March 5, 2025 at 8:02 PM
Reading this incredible paper today: The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning. What a beautiful approach to proving convrgence of Q-learning.
March 4, 2025 at 7:55 PM
Reposted by Saket
Postdocs and PhD students hit hard by Trump’s crackdown on science. Story by @heidiledford.bsky.social & @humbertobasilio.bsky.social www.nature.com/articles/d41...
Postdocs and PhD students hit hard by Trump’s crackdown on science
As US federal grants remain frozen and budget cuts loom, anxiety and fear grip early-career researchers.
www.nature.com
February 25, 2025 at 6:22 PM
ever wondered about fractional derivatives?

www.youtube.com/watch?v=2dwQ...
What Lies Between a Function and Its Derivative? | Fractional Calculus
YouTube video by Morphocular
www.youtube.com
February 24, 2025 at 8:37 PM
Interesting new take on intelligence: "Your cat is smarter than you are on certain things, and you're smarter than it on certain things". Intelligence is not a one-dimensional linear scale! www.forbes.com/sites/johnwe...
More Than One AI Revolution? Yann LeCun On Tech Trajectories
Some thoughts from experts in the field show how AI will likely unfold in the next few years.
www.forbes.com
February 21, 2025 at 9:34 PM
does anyone have good resources on the Hida
Malliavin derivative?
February 19, 2025 at 7:47 PM
pretty cool expert discussion on this year's budget www.youtube.com/live/CN-Qzke...
LIVE: Who gains, who loses in Modi 3.0's first big budget
YouTube video by The Federal
www.youtube.com
February 1, 2025 at 6:36 PM
it is kind of remarkable how you can write down crazy jolty processes as an equation like this double well stochastic process
January 9, 2025 at 2:37 AM
any CS departments doing personality hires next job season?
November 18, 2024 at 1:26 AM
live picture of me looking going through my ICLR reviews
November 15, 2024 at 5:38 PM
ever wondered why warmup the learning rate for deep learning? here's a cool paper by physicists arxiv.org/abs/2406.09405
Why Warmup the Learning Rate? Underlying Mechanisms and Improvements
It is common in deep learning to warm up the learning rate $η$, often by a linear schedule between $η_{\text{init}} = 0$ and a predetermined target $η_{\text{trgt}}$. In this paper, we show through sy...
arxiv.org
November 14, 2024 at 1:15 AM
moo deng grad student
September 24, 2024 at 11:45 PM
Andy Barto at #RLC
August 17, 2024 at 12:04 AM
Magnolias, moon and mausoleum #DALLE
June 3, 2024 at 11:39 PM
froggy
January 20, 2024 at 5:08 PM
Gentrification of Brooklyn by Dalle
December 1, 2023 at 4:01 PM
Sandstone Pillars, Zhangjiajie
November 18, 2023 at 10:55 PM
It has been a long time coming! The Reinforcement Learning Conference starting in the home of RL: rl-conference.cc
November 15, 2023 at 11:39 PM