I am in Vancouver at ICML, and tomorrow I will present our newest paper "Partially Observable Reinforcement Learning with Memory Traces". We argue that eligibility traces are more effective than sliding windows as a memory mechanism for RL in POMDPs. 🧵
16.07.2025 01:35 — 👍 59 🔁 12 💬 3 📌 3
GitHub - NishanthVAnand/eligibility_state: Eligibility state experiments.
Eligibility state experiments. Contribute to NishanthVAnand/eligibility_state development by creating an account on GitHub.
When I first started working with Doina as a master’s student 7 years ago, this was the first idea that I tried (github.com/NishanthVAna...). But, I gave up on it too soon!
I’m happy and pleased to see you explore this path in depth with a solid paper! E-traces are the best idea to come out of RL!!
17.07.2025 04:23 — 👍 2 🔁 0 💬 0 📌 0
Mila Launched Canada’s First AI Computing Cluster Dedicated to Academic Research | Mila
Mila, in partnership with Université Laval and Calcul Québec, officially launched TamIA, the first AI computing cluster specifically designed to support academic research in the country.
Introducing TamIA, the first AI computing cluster in Canada dedicated to academic research! A collaboration of Mila, Digital Research Alliance of Canada, CIFAR, Amii, @vectorinstitute.ai, Calcul Québec, Université Laval, @ualberta.bsky.social and University of Toronto. mila.quebec/en/news/mila...
24.04.2025 14:35 — 👍 9 🔁 3 💬 0 📌 0
This week, Mila researchers will present more than 90 papers at @iclr-conf.bsky.social in Singapore. Every day, we will share a schedule featuring Mila-affiliated presentations.
Day 1 👇 #ICLR2025
mila.quebec/en/news/foll...
23.04.2025 23:12 — 👍 12 🔁 3 💬 0 📌 1
Neat! What about two neural networks that have different architectures? Are there any metrics that you’re aware of could help compare them?
01.04.2025 23:19 — 👍 1 🔁 0 💬 1 📌 0
Does this mean we can evaluate the representation quality of two different neutral networks and objectively say one is better than the other?
01.04.2025 19:53 — 👍 1 🔁 0 💬 1 📌 0
Doina lab group picture
We had a lab social and the mandatory pic after 💜
22.03.2025 12:27 — 👍 1 🔁 0 💬 0 📌 0
I am hoping to contribute to this thread equally!
21.03.2025 23:27 — 👍 0 🔁 0 💬 0 📌 0
add me too please: @itsnva7.bsky.social
17.03.2025 19:13 — 👍 2 🔁 0 💬 0 📌 0
PhD Student in Tübingen (MPI-IS & Uni Tü), interested in reinforcement learning. Freedom is a pure idea. https://onnoeberhard.com/
PhD student at Mila & McGill University, Vanier scholar • 🧠+🤖 grad student• Ex-RealityLabs, Meta AI • Believer in Bio-inspired AI • Comedy+Cricket enthusiast
#RL Postdoc at Mila - Quebec AI Institute and Université de Montréal
Research Fellow @ http://openmindresearch.org interested in AI, robotics, and penguins—dabbles with game development, pixel art, speedrunning, and speedcubing.
http://kris.pengy.ca 🐧
I lead Cohere For AI. Formerly Research
Google Brain. ML Efficiency, LLMs,
@trustworthy_ml.
postdoc • neuroscience, psychedelics, RL & decision-making, ML @ McGill University / MILA Quebec AI Institute
•past Google DeepMind London / Montreal
https://veronicachelu.github.io
__
•meditation enthusiast
•yogi/200h RYT
•handbalancer/contortionist
Senior Research Scientist @MBZUAI. Focused on decision making under uncertainty, guided by practical problems in healthcare, reasoning, and biology.
computational cog sci • problem solving and social cognition • asst prof at NYU • https://codec-lab.github.io/
Neuro + AI Research Scientist at DeepMind; Affiliate Professor at Columbia Center for Theoretical Neuroscience.
Likes studying learning+memory, hippocampi, and other things brains have and do, too.
she/her.
Host TalkRL Podcast, Aspiring RL researcher
AgFunder VC Head of Eng, Ex-MSFT, Waterloo computer engineering
Sunshine Coast BC Canada
Working on scalable and decentralized algorithms for real-time reinforcement learning. Research scientist @ Keen AGI
Prev - PhD with Richard S. Sutton
PhD student at Mila and Visiting Researcher at Meta, working on the science of AI agents. Made in Sicily.
Assistant Professor in machine learning @VUAmsterdam
Abstract representations+reinforcement learning.
EEML Organizer, ML researcher
⛷️ ML Theorist carving equations and mountain trails | 🚴♂️ Biker, Climber, Adventurer | 🧠 Reinforcement Learning: Always seeking higher peaks, steeper walls and better policies.
https://ualberta.ca/~szepesva
Co-CEO, Yutori. Join the waitlist at yutori.com
Research Scientist at Google DeepMind and Professor of Computer Science and Engineering at the University of Michigan. Interested in Reinforcement Learning and Artificial Intelligence.
Thinking about AI and RL.
Fellow @ Openmind Research Institute
Adjunct Prof. @ University of Alberta
Scientist @ DeepMind and Honorary Fellow @ U of Edinburgh.
RL, agency, philosophy, foundations, AI.
https://david-abel.github.io
Señor swesearcher @ Google DeepMind, adjunct prof at Université de Montréal and Mila. Musician. From 🇪🇨 living in 🇨🇦.
https://psc-g.github.io/
