Arsenii Kuznetsov
Research Assistant at Mila - Quebec Artificial Intelligence Institute
Canada
Summary
👤
Senior🎓
Top SchoolArsenii Kuznetsov is a Deep Learning Research Engineer with a decade of experience applying reinforcement learning and computer vision to both research and product problems. He has led publication-oriented work at Samsung AI Center—publishing at CVPR and ICML and earning a Samsung Best Paper Bronze award—and now contributes to research at Mila in Canada. His background spans malware detection and applied ML systems from Kaspersky to hands-on software development at Yandex, giving him a rare blend of security-minded production engineering and theoretical RL expertise. He specializes in partially observable MDPs, credit assignment, meta-RL and correcting overestimation bias in continuous control, and is comfortable moving ideas from conference-ready research to product features like interactive segmentation. An interesting thread through his career is translating academic Bayesian-methods rigor into deployable ML systems that address real-world constraints.
10 years of coding experience
9 years of employment as a software developer
Master's degree, Computational and Applied Mathematics, Master's degree, Computational and Applied Mathematics at Moscow State UniversityArtificial Intelligence, Artificial Intelligence at Yandex School of Data Analysis
Github Skills (53)
dataflow9
portable9
xgboost9
java9
gradient9
machine-learning9
distributed-systems9
gymnasium9
truncated9
scalable9
q-learning9
python8
boosting8
reinforcement-learning8
quantile8
Programming languages (2)
Github contributions (5)
SamsungLabs/tqc
Feb 2020 - Nov 2020
Implementation of Truncated Quantile Critics method for continuous reinforcement learning.
Contributions:3 commits, 1 push, 1 branch in 9 months
maximumentropyactor-criticreinforcement-learningcontinuous
SamsungLabs/tqc_pytorch
Apr 2020 - Feb 2021
Implementation of Truncated Quantile Critics method for continuous reinforcement learning. https://bayesgroup.github.io/tqc/
Contributions:3 commits, 2 PRs, 2 pushes in 10 months
actor-criticreinforcement-learningcontinuousmethodquantile
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.