Pablo G Morato

Yes, it’s crazy windy! It’s not too cold in winter though. Have you found any tips by now?

31.12.2024 11:44 — 👍 1    🔁 0    💬 1    📌 0

yes, the acceptable failure probability set for aircraft systems is very low, usually lower than 10^-8 per flight/hour (annual failure prob lower than 10^-5, compared to 10^-3 - 10^-5 annual failure prob for bridges). Risk perception is influenced by the limited control one has over such situations.

30.12.2024 23:08 — 👍 4    🔁 0    💬 0    📌 0

Learn Git Branching An interactive Git visualization tool to educate and challenge!

On one of the first projects I supervised in my PhD, a student repeatedly ignored suggestions to commit and then accidentally deleted the project at the end of the semester. Please use git! There are even "fun" games you can use to learn it:
learngitbranching.js.org

27.11.2024 15:40 — 👍 60    🔁 6    💬 5    📌 0

As my first post on this platform, allow me to advertise the RL theory lecture notes I have been developing with Sasha Rakhlin: arxiv.org/abs/2312.16730

(shameless repost of my pinned tweet)

21.11.2024 14:48 — 👍 211    🔁 34    💬 4    📌 1

Trying to build a "books you must read" list for my lab that everyone gets when they enter. Right now its:

- Sutton and Barto
- The Structure of Scientific Revolutions
- Strunk and White
- Maybe "Prediction, Learning, and Games", TBD

Kinda curious what's missing in an RL / science curriculum

25.11.2024 17:43 — 👍 141    🔁 11    💬 36    📌 1

Want to learn / teach RL? 

Check out new book draft:
Reinforcement Learning - Foundations
sites.google.com/view/rlfound...
W/ Shie Mannor & Yishay Mansour
This is a rigorous first course in RL, based on our teaching at TAU CS and Technion ECE.

25.11.2024 12:08 — 👍 154    🔁 34    💬 4    📌 4

I'd love to join if there are any spaces left :)

24.11.2024 18:19 — 👍 1    🔁 0    💬 1    📌 0

Thanks! :)

24.11.2024 16:46 — 👍 0    🔁 0    💬 0    📌 0

I'd like to be added :) Working on computer vision and MARL 🍒

24.11.2024 16:06 — 👍 1    🔁 0    💬 1    📌 0

Any suggestions for quantifying uncertainty in predictions made by pre-trained computer vision models (such as DINO)? #computervision

23.11.2024 17:15 — 👍 3    🔁 0    💬 0    📌 0

Yes, this last option seems more compelling 🤣

21.11.2024 18:14 — 👍 1    🔁 0    💬 0    📌 0

Reviewer 2 pointed out that a core weakness of my algorithm is that "it is relatively straightforward". To me, this comment feels more positive than negative. Has anybody received similar comments? How would you reply to that?

21.11.2024 11:58 — 👍 0    🔁 0    💬 1    📌 0

Trying to slowly populate the RL list here, help me out: go.bsky.app/3WPHcHg

14.09.2024 20:53 — 👍 72    🔁 32    💬 17    📌 2