Igor Kuznetsov
Hallo! I am a master's student in Computational Modeling and Simulation programme at TU Dresden focusing on differential simulations for AI. Broadly, I am interested in adaptive AI systems capable of operating robustly in a lifelong open-ended manner, usually in the context of Reinforcement Learning. To this end, I am focused on researching world models and persistent memory, equipping embodied agents with abilities to perform reasoning in complex environments based on their past experience. I am a slow thinker and in my free time enjoy listening to Japanese ambient and wandering around new cities taking photos.igorkuznetsov14 [at] gmail [dot] com
Safer Reinforcement Learning by Going Off-policy: a Benchmark
Guided Exploration in Reinforcement Learning via Monte Carlo Critic Optimization
AAMAS, 2024 / DARL Workshop @ ICML, 2022
Conditioning of Reinforcement Learning Agents and its Policy Regularization Application
Research and Development Experience
2023-2025
Oxa (Oxford, UK), Research Engineer
Reinforcement Learning for AV scenarios generation in simulation
2020-2023
Giant.AI [robotics start-up] (Campbell, CA) Machine Learning Engineer
Reinforcement Learning and Imitation Learning for humanoid robots
2020
JetBrains Research (St. Petersburg, Russia) Intern
Reinforcement Learning research (Autonomous Agents Group)
2017-2019
Insilico Medicine (St. Petersburg, Russia), Data Scientist
Machine Learning for Small Molecules Property Prediction
Education
2025 - Present
TU Dresden, Germany
MSc in Computational Modeling and Simulation (AI Track)
2017 - 2021
ITMO University, St. Petersburg, Russia
BSc in Computer Science and Computer Engineering
Summer Schools 🎒
2025
Sarajevo, Bosnia and Herzegovina
Tools
Python, Vim, Git
Languages
Fluent
English
Beginner
German
Native
Russian