Head of AI Research in a fintech company. Decision Making in the Wild. Opinions are my own.
Joined May 2011
- Tweets589
- Following239
- Followers1.2K
- Likes1.5K
Sergey Kolesnikov retweeted
1/7 In-context learning (ICL) is poised to revolutionise NLP, but its success hinges on our ability to process long sequences. Recently, @simran_s_arora et al. showcased advancements in Linear Transformers and proposed Based. But what if we could push its boundaries further?
Sergey Kolesnikov retweeted
Our first stable release and full paper preprint for XLand-MiniGrid is done, check it out! Compared to the workshop version, we have significantly redesigned the library, multi-GPU baselines and standardized benchmarks with millions of unique tasks.
github.com/corl-team/xland-m…
Sergey Kolesnikov retweeted
In-Context RL for Variable Action Spaces
ICRL is a promising direction to build Foundational Decision-Making Models. But adaptation to new action spaces is a problem.
We propose Headless Algorithm Distillation (@MishaLaskin) to address it.
arxiv.org/abs/2312.13327
Sergey Kolesnikov retweeted
Which data-collection strategies enable In-Context Reinforcement Learning?
You need either RL training trajectories or supervision with optimal actions. But what if we had a demonstrator policy, could we use it to enable ICRL? We show the answer is yes
arxiv.org/abs/2312.12275
Sergey Kolesnikov retweeted
🔥 Imagine if you could train Meta-RL agents for 1 TRILLION transitions under 40 hours?
We present XLand-MiniGrid — JAX-accelerated meta-reinforcement learning environments inspired by XLand (@FeryalMP) and MiniGrid (@Love2Code).
code: github.com/corl-team/xland-m…
Sergey Kolesnikov retweeted
NetHack is arguably one of the most challenging games for humans and even more for RL algorithms. Maybe, offline RL could help? Time will reveal.
To bootstrap the practitioners, we release Katakomba — Tools and Benchmarks for Data-Driven NetHack.
github.com/tinkoff-ai/katako…
Sergey Kolesnikov retweeted
Interested in offline and offline-to-online RL 🫶? Check out new major release of Clean Offline Reinforcement Learning library:
🤖 Offline: 10 algorithms, 30 datasets benchmarked
🦾 Offline-to-Online: 5 algorithms, 10 datasets benchmarked
github.com/tinkoff-ai/CORL
Sergey Kolesnikov retweeted
Check out our blog post for a thorough explanation of how brainchop.org was made and the principles behind its work. With @MMasoud2021 @FarfallaHu @Entodi @Kevin_C_Wang @Scitator
#neuroimaging #brainresearch #medicalresearch #MRI #MadeWithTFJS
trendscenter.org/in-browser-…
Sergey Kolesnikov retweeted
Hi guys, nice project!
It was an intense month for was, so check out the Catalyst 21.11 release:
t2m.io/wQEbaHa
And stay tuned for more updates 🚀
#opensource #deeplearning #pytorch #catalyst
Sergey Kolesnikov retweeted
Build a 3D Brain Segmentation Pipeline for MRI with Catalyst a PyTorch framework for Deep Learning Research and Development
$ pip install -U catalyst
@Scitator
@PyTorch
@Entodi
medium.com/pytorch/catalyst-…
github.com/catalyst-team/cat…
Sergey Kolesnikov retweeted
[RU] I am thrilled to share with you a new Deep Learning library focused on neural network models compression! Check the video below for more details!
youtu.be/UoN1iwEIux0 youtu.be/UoN1iwEIux0
Sergey Kolesnikov retweeted
[RU] In this video, I would like to share with you the "Deep Learning with Catalyst" course creation. Feel free to write any questions about the course :)
youtu.be/uJLI51hHIWc youtu.be/uJLI51hHIWc
Sergey Kolesnikov retweeted
Thanks to Wandb team, you could now monitor your Catalyst experiments easily.
Check the new demo: youtu.be/Rs3Ne29ycgk youtu.be/Rs3Ne29ycgk
Sergey Kolesnikov retweeted
I am happy to share the joint Catalyst and Neptune demo on "Catalyst experiments logging with Neptune", so you could log all your deep learning experiments like a pro!
youtu.be/qsPnXUOKjVA youtu.be/qsPnXUOKjVA
Sergey Kolesnikov retweeted
Dear all, we are happy to introduce Catalyst Workshop 🎉
Tomorrow at 14 pm Moscow time we will dive into Catalyst (and RL) best practices at ods.ai!
Our speakers thread:
Sergey Kolesnikov retweeted
Great news for the great community: renewed Catalyst introduction post with lots of @PyTorch examples.
Write code with PyTorch, accelerate it with Catalyst!
medium.com/pytorch/catalyst-…
Sergey Kolesnikov retweeted
Another one – reinforcement learning with Catalyst:
github.com/catalyst-team/cat…
More tutorials are on their way 🚀
Write code with @PyTorch, accelerate it with Catalyst!
Sergey Kolesnikov retweeted
New tutorials with Catalyst are here! 🎉
Check out our step-by-step guide on PyTorch train loop decomposition with Catalyst:
colab.research.google.com/gi…
#tutorial #catalyst #pytorch #colaboratory colab.research.google.com/gi…
