Missed our workshop at @rl-conference.bsky.social?
Watch all keynote presentations and the panel discussion on YouTube:
youtube.com/playlist?lis...
Big thanks to our awesome speakers: @togelius.bsky.social, @jmac-ai.bsky.social, Roberta Raileanu, Michael Bowling and @pcastr.bsky.social!
Exciting news - early bird registration is now open for #RLDM2025!
🔗 Register now: forms.gle/QZS1GkZhYGRF...
Register now to save €100 on your ticket. Early bird prices are only available until 1st April.
Doing some slides on reinforcement learning, and passing through k-armed bandits along the way.
The phrase "Optimism under uncertainty is a simple, effective, and in some cases optimal way to minimize regret" hits different these days.
If you like Reinforcement Learning, I created a feed that tracks recent popular posts on the topic:
#RL #RLHF #ReinforcementLearning
I used the DeepSeek Reinforcement Learning GRPO algorithm to train a triangle creature. The edges are "muscles": red=extend, blue=contract; vertices are "mass pumps": red=grow, blue=shrink. Reward = DeltaX - |DeltaY|. Full video incoming: Subscribe at www.youtube.com/@MihaiNicaMath
On the migration of the scientific community to Bluesky:
www.nature.com/articles/d41... 🧪
A gazelle calf struggles to its feet minutes after being born. Half an hour later it is running at 20 miles per hour.
1/ I was looking through Sutton and Barto's "Reinforcement Learning" book and it had this remarkable claim, so I Googled it. Can you guess what the response was? [little 🧵] ↵
Excited to announce that I’m teaming up with @quillmatiq.com on a new non-profit for the open social web, across protocols, with Bridgy Fed as its first main project! Introducing A New Social.
📚📢Christmas came early 🎅
Our new textbook on multi-agent reinforcement learning with @mitpress.bsky.social is out NOW!
The book is available from MIT Press (mitpress.mit.edu/978026204937...) or your bookstore nearby.
Why you should be interested, what you get, and more all in a 🧵👇
Data Science Environment Away day going very well indeed - after a morning of presentations a well deserved lunch break!
We did it! 1st use of VR in teaching at @lancasteruni.bsky.social taking our students to an underwater world 😃 includes data collected from our lovely students to allow us to assess its effectiveness. Thanks to The Hydrous for providing the underwater coral reef experience FREE thehydro.us
Be great to link up with any Lancaster University people on this site @bsky.app
Likewise!
An updated intro to reinforcement learning by Kevin Murphy: arxiv.org/abs/2412.05265! Like their books, it covers a lot and is quite up to date with modern approaches. It also is pretty unique in coverage, I don't think a lot of this is synthesized anywhere else yet
This is one I've wanted to do for a while: ask why RL has been continually underestimated in the last 2 years.
Interviewing Finbarr Timbers on the "We are So Back" Era of Reinforcement Learning
Interconnects interview #11. An overview on the past, present, and future of RL.
https://buff.ly/3Vqrbqj
Check out my article on Reinforcement Learning for the Open Encyclopedia of Cognitive Science! oecs.mit.edu/pub/k2ek981x...
@oecs-bot.bsky.social
Just starting to build out my home office to have a nice space to push through the end of my PhD. What's your number one item to have in it? Can be anything from plants to monitors!
🌊🧪
#phdlife
#academia
The deep goal of bluesky is to decentralize the social internet so that every individual controls their experience of it rather than having it be controlled by 5 random billionaires. Everyone thinks they signed up for a demuskified twitter...we actually signed an exciting and bizarre experiment.
How come I didn't know about this BeNeRL seminar series? It focuses on practical RL and seems really great!
www.benerl.org/seminar-seri...
I would have loved to hear Benjamin Eysenbach, Chris Lu and Edward Hu... Next one is on December 19th.
Reinforcement learning (RL) remains surprisingly brittle to contextual variations in tasks. Our new method (NeurIPS 2024) for solving contextual RL problems achieves 5-50x better sample efficiency on standard & traffic benchmarks. Featured by MIT news! news.mit.edu/2024/mit-res...
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.
Streaming Deep Reinforcement Learning Finally Works, by
M. Elsayed, G. Vasan, A. R. Mahmood, is one of those papers I wish I had written 😅
This paper seems to allow us to do RL with NNs as it should have always been done. Everyone should read it!
arxiv.org/abs/2410.14606
Adding my love letter to
arxiv.org/pdf/2304.01315
Empirical Design in Reinforcement Learning
by
Andrew Patterson, Samuel Neumann, Martha White, Adam White
JMLR 25 (2024) 1-63
#ReinforcementLearning
These aren’t the heroes we deserve, but they are the heroes we need.
Does everyone in your community agree on some folk knowledge that isn’t published anywhere? Put it in a paper! It’s a pretty valuable contribution
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
