About Me
Lead Research Scientist @ Reinforcement Learning Team @ Tinkoff
Research Interests
- Reinforcement Learning (esp. Offline)
- Causality (applications to out-of-distribution generalization, transfer learning)
- Recommender Systems (esp. using Reinforcement Learning)
Publications
-
Revisiting the Minimalist Approach to Offline Reinforcement Learning*
NeurIPS, 2023
Denis Tarasov, Vladislav Kurenkov, Alexander Nikulin, Sergey Kolesnikov
[arXiv] [src] -
Katakomba: Tools and Benchmarks for Data-Driven NetHack
NeurIPS, 2023
Vladislav Kurenkov, Alexander Nikulin, Denis Tarasov, Sergey Kolesnikov
[arXiv] [src] -
CORL: Research-oriented Deep Offline Reinforcement Learning Library
NeurIPS, 2023
NeurIPS, 3nd Offline Reinforcement Learning Workshop, 2022
Denis Tarasov, Alexander Nikulin, Dmitry Akimov, Vladislav Kurenkov, Sergey Kolesnikov
[arXiv] [src] -
Anti-Exploration by Random Network Distillation
ICML, Main, 2023
Alexander Nikulin, Vladislav Kurenkov, Denis Tarasov, Sergey Kolesnikov
[arXiv] [src] -
Q-Ensemble for Offline RL: Don’t Scale the Ensemble, Scale the Batch Size
NeurIPS, 3nd Offline Reinforcement Learning Workshop, 2022
Alexander Nikulin, Vladislav Kurenkov, Denis Tarasov, Dmitry Akimov, Sergey Kolesnikov
[arXiv] [src] -
Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows
NeurIPS, 3nd Offline Reinforcement Learning Workshop, 2022
Dmitriy Akimov, Vladislav Kurenkov, Alexander Nikulin, Denis Tarasov, Sergey Kolesnikov
[arXiv] [src] -
Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters
ICML, Main, Spotlight, 2022
NeurIPS, 2nd Offline Reinforcement Learning Workshop, 2021
Vladislav Kurenkov, Sergey Kolesnikov
[arXiv] [src] -
Prompts and Pre-Trained Language Models for Offline Reinforcement Learning
ICLR, Workshop on Generalizable Policy Learning in the Physical World, 2022
ACL, Workshop on Learning with Natural Language Supervision, 2022
Denis Tarasov, Vladislav Kurenkov, Sergey Kolesnikov -
Guiding Evolutionary Strategies by Differentiable Robot Simulators
NeurIPS, 4th Robot Learning Workshop, 2021
Vladislav Kurenkov, Bulat Maksudov
[arXiv] [src] -
Task-Oriented Language Grounding for Language Input with Multiple Sub-Goals of Non-Linear Order
EEML, 2020
Vladislav Kurenkov, Bulat Maksudov, Adil Khan
[arXiv] [src] -
Learning Stabilizing Control Policies for a Tensegrity Hopper with Augmented Random Search
IEEE ICIEAM, 2020
Vladislav Kurenkov, Hany Hamed, Sergei Savin
[ieee] [arXiv] [src] -
[RU] Mathematical Modeling of Tensegrity Robots with Rigid Rods
Computer Research and Modeling, 2020
Sergei Savin, Lyudmila Vorochaeva, Vladislav Kurenkov
[mathnet] [src]
Pet Projects
- [Telegram Channel] causality links
- [Telegram Channel] Екатерина Шульман (нейро)
Contact
- Email: v[dot]kurenkov{at}innopolis{dot}ru
- Telegram: @vkurenkov
- Twitter: vladkurenkov