I am Head of AI Research at Tinkoff, an AI-first fintech company. Our team is focused on the CV, NLP, RL, and RecSys domains to advance the AI field and create novel technical solutions. We also frequently launch students' projects through TLab.
My own line of research is mainly focused on sequential decision-making under uncertainty and ML robustness. Besides that, I help with the Tinkoff.AI meetups organization and advise the MLE profession within Tinkoff.
In my spare time, I actively contribute to open-source projects and lead the development of Catalyst, an open-source PyTorch framework for deep learning research and development. I also recently launched Animus as a framework-less alternative to organize research experiments.
Short notes in Decision Making in the Wild.
High-quality single-file implementations of SOTA Offline RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC
Minimalistic framework to run machine learning experiments
4th place solution for the SIGIR 2021 challenge.
Time Series Library
A tiny Catalyst-like experiment runner framework on top of micrograd.
Advanced deep learning course
Checklist and questions to make ML right.
Accelerated Python code formatter
Brief introduction to Reinforcement Learning and Recommender Systems.
Experiments logging & visualization
2nd place solution for NeurIPS RL 2019 challenge
Convenient deep learning models serving
Object detection with Catalyst
Image segmentation with Catalyst
Image classification with Catalyst
Distributed framework for RL research
Accelerated deep learning research and development
3rd place solution for NeurIPS RL 2018 challenge
4th place solution for OpenAI Retro Contest.
3rd place solution for NIPS RL 2017 challenge