Ilya Zisman

Hi! I'm an MSc student at Higher School of Economics and a Research Scientist at Tinkoff. My passion is Deep Reinforcement Learning in all its diversity. Previously I worked at JetBrains Research, Hamburg University of Technology and Robert Bosch R&D.

github / scholar
ilyazisman at gmail dot com

Publications

I'm interested in deep reinforcement learning, imitation learning and sequential decision making.

	Emergence of In-Context Reinforcement Learning from Noise Distillation Ilya Zisman, Vladislav Kurenkov, Alexander Nikulin, Viacheslav Sinii, Sergey Kolesnikov arXiv, 2024 arxiv / code (soon) /
	XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX Alexander Nikulin, Vladislav Kurenkov, Ilya Zisman, Artem Agarkov, Viacheslav Sinii, Sergey Kolesnikov arXiv, 2024 arxiv / code /
	In-Context Reinforcement Learning for Variable Action Spaces Viacheslav Sinii, Alexander Nikulin, Vladislav Kurenkov, Ilya Zisman, Sergey Kolesnikov arXiv, 2024 arxiv / code (soon) /
	Mediated Multi-Agent Reinforcement Learning Dmitry Ivanov, Ilya Zisman, Kirill Chernyshev AAMAS, 2023 arxiv / code (soon) /
	Machine learning models for photonic crystals band diagram prediction and gap optimisation Alexander Nikulin, Ilya Zisman, Manfred Eich, A.Y. Petrov, Alexander Itin Photonics and Nanostructures - Fundamentals and Applications, 2022 pdf / code (soon) /

Design and source code from Leonid Keselman's website

Ilya Zisman

Publications

Emergence of In-Context Reinforcement Learning from Noise Distillation

XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX

In-Context Reinforcement Learning for Variable Action Spaces

Mediated Multi-Agent Reinforcement Learning

Machine learning models for photonic crystals band diagram prediction and gap optimisation