Padideh Nouri(@PadidehNOURI) 's Twitter Profileg
Padideh Nouri

@PadidehNOURI

RL, deep learning @Mila_Quebec

ID:1269727305305382913

linkhttps://informaticspadideh.com/ calendar_today07-06-2020 20:27:16

40 Tweets

335 Followers

583 Following

Follow People
Tristan Deleu(@TristanDeleu) 's Twitter Profile Photo

New paper 📄 'Discrete Probabilistic Inference as Control in Multi-path Environments', joint work with Padideh Nouri, Nikolay Malkin, Doina Precup & Yoshua Bengio MilaQuebec

Paper 📄: arxiv.org/abs/2402.10309
Code 🖥: github.com/tristandeleu/g…

New paper 📄 'Discrete Probabilistic Inference as Control in Multi-path Environments', joint work with @PadidehNOURI, Nikolay Malkin, Doina Precup & Yoshua Bengio @Mila_Quebec Paper 📄: arxiv.org/abs/2402.10309 Code 🖥: github.com/tristandeleu/g…
account_circle
David Yu-Tung Hui(@dythui) 's Twitter Profile Photo

Did you know that deep Q-learning implicitly has two Gumbel noise sources?
Accounting for these noise sources yields aggregate empirical improvements.

Double Gumbel Q-Learning is a spotlight paper with Aaron Courville Pierre-Luc Bacon.

I'll present it 5-7 Dec 13 NeurIPS Conference #1502.

Did you know that deep Q-learning implicitly has two Gumbel noise sources? Accounting for these noise sources yields aggregate empirical improvements. Double Gumbel Q-Learning is a spotlight paper with @AaronCourville @pierrelux. I'll present it 5-7 Dec 13 @NeurIPSConf #1502.
account_circle
Valence Labs(@valence_ai) 's Twitter Profile Photo

Valence Labs will be co-hosting a TechBio social with @recursionpharma and NVIDIA at .

Join us on Wed, Dec 13th. RSVP here: lu.ma/5wx660v2

Our team will also be at throughout the week. See below for a summary of our papers👇

account_circle
MilaQuebec(@Mila_Quebec) 's Twitter Profile Photo

From November 8 to 10, Mila will be holding its first workshop on generative flow networks (GFlowNets).

Save this link and join us online tomorrow as of 9:30am : youtube.com/@mila-quebecar…

From November 8 to 10, Mila will be holding its first workshop on generative flow networks (GFlowNets). Save this link and join us online tomorrow as of 9:30am : youtube.com/@mila-quebecar…
account_circle
Pierluca D'Oro(@proceduralia) 's Twitter Profile Photo

Can reinforcement learning from AI feedback unlock new capabilities in AI agents?

Introducing Motif, an LLM-powered method for intrinsic motivation from AI feedback. Motif extracts reward functions from Llama 2's preferences and uses them to train agents with reinforcement

account_circle
Amir-massoud Farahmand(@SoloGen) 's Twitter Profile Photo

A year ago today Mahsa Amini was killed by the thugs of the Islamic Republic of Iran. She was not the first and has not been the last to be demised by the IR in the past 44 years, but she was the butterfly that fundamentally changed most Iranians.

account_circle
Arushi Jain(@arushijain130) 's Twitter Profile Photo

👩‍💻💪Encouraging women to have access to mentorship is essential for fostering diversity and inclusivity in ML. Join the WiML breakout session on 'Role of Mentorship and Networking' at .
🗓️ 28th July, 11-12
📍 Room 326 A

account_circle
Sangnie Bhardwaj(@sangnie) 's Twitter Profile Photo

Join us at the WiML Un-Workshop breakout session on 'Role of Mentorship and Networking'! Do not miss the chance to talk with leading researchers Samy Bengio, Susan Zhang Hugo Larochelle Sharon Y. Li Pablo Samuel Castro John Langford and others!
WiML

account_circle
MilaQuebec(@Mila_Quebec) 's Twitter Profile Photo

Professor Bengio’s research group is currently looking to fill two postdoctoral positions in machine learning for drug discovery as part of a collaboration with Recursion Pharmaceuticals.

Learn more 👉 pulse.ly/mi4jc3ha3u

account_circle
Elham Azizi(@elhamazizi) 's Twitter Profile Photo

Almost 1200 innocent school girls across 15 cities in Iran have been the target of systematic gas attacks and poisoning *inside* schools. This biological terrorizing is suspected to be carried out by hardliners to stop girls from going to school Malala Yousafzai's story is not far away 😔

Almost 1200 innocent school girls across 15 cities in Iran have been the target of systematic gas attacks and poisoning *inside* schools. This biological terrorizing is suspected to be carried out by hardliners to stop girls from going to school @Malala's story is not far away 😔
account_circle
Padideh Nouri(@PadidehNOURI) 's Twitter Profile Photo

Wishing everyone a happy holiday season! 🎁
If you are looking for a fun and informative read for your holidays, try checking out 'The GFlowNet Tutorial' (milayb.notion.site/The-GFlowNet-T…). It gives a great introduction to the GFlowNets and provides references if you want to read further

account_circle
Padideh Nouri(@PadidehNOURI) 's Twitter Profile Photo

At New Orleans for ! See you at MLSB @ NeurIPS this Saturday to discuss our recent paper 'Designing Biological Sequences via Meta-Reinforcement Learning and Bayesian Optimization' (arxiv.org/abs/2209.06259) 🔥

account_circle
Kyunghyun Cho(@kchonyc) 's Twitter Profile Photo

here’s the slide deck i used at ML in PL 2022 last week. here we give a brief intermediate report on Prescient Design ‘s effort in ML toward lab-in-the-loop molecular design. one teaser: it won’t be one algorithm that’ll solve this problem.

drive.google.com/file/d/1spTU-i…

account_circle
Padideh Nouri(@PadidehNOURI) 's Twitter Profile Photo

Charity conference co-organized by some wonderful Mila students. Please consider donating and sharing this with others 🙂

account_circle
Sergey Levine(@svlevine) 's Twitter Profile Photo

In theory RL is intractable w/o exploration bonuses. In practice, we rarely use them. What's up with that? Critical to practical RL is reward shaping, but there is little theory about it. Our new paper analyzes sample complexity w/ shaped rewards: arxiv.org/abs/2210.09579

Thread:

In theory RL is intractable w/o exploration bonuses. In practice, we rarely use them. What's up with that? Critical to practical RL is reward shaping, but there is little theory about it. Our new paper analyzes sample complexity w/ shaped rewards: arxiv.org/abs/2210.09579 Thread:
account_circle
Firouz M. Naderi(@Firouz_Naderi) 's Twitter Profile Photo

Can you imagine the US government sending armed guerrilla forces to Boston to surround Harvard and MIT and start killing students? Well, that is exactly what is going on in Tehran, Iran as I tweet this. The world media seems to be deaf and blind!!

account_circle
Justin Trudeau(@JustinTrudeau) 's Twitter Profile Photo

.Bundeskanzler Olaf Scholz Scholz and I often talk about how our two countries can work together. Today, @MILA_Quebec showed us what that can look like in AI – with real-world applications – and how that partnership can create good jobs and new opportunities for both Canadians and Germans.

.@Bundeskanzler Scholz and I often talk about how our two countries can work together. Today, @MILA_Quebec showed us what that can look like in AI – with real-world applications – and how that partnership can create good jobs and new opportunities for both Canadians and Germans.
account_circle