Head of AI Research in a fintech company. Decision Making in the Wild. Opinions are my own.
Joined May 2011
- Tweets 589
- Following 237
- Followers 1,200
- Likes 1,534
142 Photos and videos
Pinned Tweet
30 Dec 2022
This year we managed to do the impossible. We launched the AI research department, and we launched it noticeably – with recognition from the world's leading AI conferences: ICML and NeurIPS (both spotlights). But I want to believe that this is just the beginning...
1
1
5
1,194
Sergey Kolesnikov retweeted
19 Feb 2024
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?
2
26
83
14,180
Sergey Kolesnikov retweeted
13 Feb 2024
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…
1
7
22
2,579
Sergey Kolesnikov retweeted
12 Feb 2024
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
1
19
104
9,179
Sergey Kolesnikov retweeted
9 Feb 2024
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
1
10
40
5,294
Sergey Kolesnikov retweeted
4 Dec 2023
🔥 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…
2
31
181
30,879
Sergey Kolesnikov retweeted
16 Jun 2023
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…
2
18
84
30,858
Sergey Kolesnikov retweeted
15 Jun 2023
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
2
9
53
9,254
18 May 2023
📢 Exciting research from our team! We explored the power of seemingly minor design choices in offline RL by applying them to an established minimalistic baseline developed by @shaneguML. The outcome? Just follow this 🧵
18 May 2023
There were a lot of algorithmic innovations in offline RL recently, along with a silent evolution of minor design choices.
What if we applied these seemingly minor modifications to an established minimalistic baseline by @shaneguML? Turns out, gains are enormous.
2
360
28 Apr 2023
Exciting news: Our paper has been accepted at ICML! Our work focuses on improving the reliability of offline RL algorithms and tackling overfitting through an anti-exploration bonus. And the best part? SAC-RND challenges SOTA results with a single network, no ensembles required!
1
4
12
1,243
30 Dec 2022
This year we managed to do the impossible. We launched the AI research department, and we launched it noticeably – with recognition from the world's leading AI conferences: ICML and NeurIPS (both spotlights). But I want to believe that this is just the beginning...
1
1
5
1,194
30 Dec 2022
For a full list of our publications, check my unofficial records 😅
notion.so/scitator/TRS-Paper…
1
281
21 Jul 2022
Optimizing accuracy is not a problem if you are EXACT 🤘
21 Jul 2022
In our new paper 🚀 we optimize accuracy via gradient descent! The work, called "EXACT: How to Train Your Accuracy", will be presented at the TAG-ML workshop during #ICML2022 🙃
Paper: arxiv.org/pdf/2205.09615.pdf
Poster: drive.google.com/file/d/1ZBO…
Enjoy!)
3
20 Jul 2022
You don't need a TPU cluster to count a budget 🤯
Join our EOP talk (@vladkurenkov) in room 307 in 2 hours!
@icmlconf spotlight, #ICML2022
6
7 Jun 2022
Are you ready for the upcoming ICML spotlight? 🤯
kudos to @vladkurenkov
7 Jun 2022
Extremely pleased to announce that our paper “Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters” was accepted to ICML 2022 (Spotlight)!
tinkoff-ai.github.io/eop
(1/N)
3
28 Apr 2022
If you're at ICLR now, check Generalizable Policy Learning in the Physical World workshop tomorrow. We will present Prompts and Pre-Trained Language Models for Offline Reinforcement Learning and will be happy to share its current improvements. We have some 😉
1
2
8
Sergey Kolesnikov retweeted
27 Apr 2022
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-…
7
21
23 Feb 2022
I was experimenting with Self-Supervised Learning recently, so if you are interested in easy to go implementations for Barlow-Twins, BYOL, SimClR, or Supervised contrastive - check out the repo: bit.ly/3H9OgUa
Comparison results included!
5
21 Feb 2022
Long time no see, my friends!
I am thrilled to present you with a new year update of the Catalyst - PyTorch high-level API to accelerate your R&D.
Bunch of improvements and simplifications, check out updated examples for more:
bit.ly/3v4nw53
3
14 Feb 2022
Interested in Offline RL?
We have recently updated our work on Online Evaluation Performance: bit.ly/3rNljZP
Open for your questions in the thread!
1
6