teaching

  • Lectures on Reinforcement Learning in AI master’s program (Moscow Institute of Physics and Technology, Phystech School of Applied Mathematics and Informatics)
  • Lectures on Introduction in AI in AI master’s program (MIPT)
  • Seminar on Intelligent Data Mining (National Research University Higher School of Economics, Faculty of Computer Science)
  • Lectures on Intelligent Dynamic Systems, Theoretical Computer Science, and Intelligent Data Analysis (Peoples’ Friendship University of Russia, Department of Computer Science)
  • Scientific advisor of PhD these:
    • Petr Kuderov (2024, MIPT, “Development of methods and algorithms for information representation in reinforcement learning using biological principles”)
    • Mais Jamal (2024, MIPT, “Development and research of methods and algorithms for adaptive maneuver planning of an unmanned vehicle”)
    • Brian Angulo (2024, MIPT, “Planning the trajectory of a mobile agent, taking into account kinematic constraints, based on classical and learnable methods”)
    • Alexey Staroverov (2023, MIPT, “Methods and algorithms of learnable visual navigation of mobile robots”)
    • Alexey Skynnik (2023, MIPT, “Reinforcement learning method for navigation tasks”)
    • Alexey Kovalev (2022, HSE, “Methods and algorithms of neuro-symbolic scene representation in multimodal tasks”)
  • Scientific advisor of master’s these at MIPT:
    • Georgy Gorbov (2023, “Adaptive maneur planning in Apollo platform”)
    • Mikhail Melkumov (2023, “Offline reinforcement learning in interactive planning for road intersection scenarios”)
    • Maria Nesterova (2023, “Curriculum reinforcement learning in a multi-agent pathfinding problem for partially observable environments”)
    • Yelisey Pitanov (2023, “Monte-Carlo tree search and reinforcement learning in a multi-agent planning task”)
    • Kristina Sarkisyan (2023, “Language models and prompting in multimodal tasks of agent’s behavior generation”)
    • Leonid Ugadiarov (2023, “Object-oriented decomposition of world model in reinforcement learning”)
    • Igor Shimanogov (2023, “Object-oriented reinforcement learning in game environments”)
    • Eugeni Dzjivelikyan (2022, “Algorithms for modeling goal-oriented behavior using hierarchical temporal memory”)
    • Daniil Kirilenko (2022, “Visual question answering for the task of navigating robotic platforms”)
    • Artem Latyshev (2022, “Modeling intrinsic motivation in hierarchical temporal memory”)
    • Artem Zholus (2022, “Generalization of tasks for robotic control with trainable models of the world”)