2025/2026
Математика обучения с подкреплением
Статус:
Маго-лего
Где читается:
Факультет компьютерных наук
Когда читается:
2 модуль
Охват аудитории:
для своего кампуса
Язык:
английский
Кредиты:
3
Контактные часы:
28
Course Syllabus
Abstract
Reinforcement learning is a type of machine learning. The key feature of this method, unlike classical machine learning, is the interaction of the agent (algorithm) with an environment from which he receives feedback in the form of rewards. The agent's goal is to maximize the sum of rewards that the environment gives him for the "right" interaction. During the course, we will get acquainted with the basic concepts of reinforcement learning theory, talk about the exploration of the environment and the paradigm of optimism. We also study modern reinforcement learning algorithms such as TRPO, PPO, and entropic reinforcement learning, which are widely used, for example, in modern methods of training large language models.
Learning Objectives
- Understanding mathematical fundamentals of modern reinforcement learning methods.
Expected Learning Outcomes
- The ability to apply mathematical methods for the analysis of reinforcement learning algorithms
- The ability to construct the effective algorithms
- Developing the skill of problem-solving and understanding algorithms
Course Contents
- Introduction to stochastic multi-armed bandits.
- Policy Evaluation
- Learning in MDP
- Exploration in MDP
- General state space MDP
- Policy optimization
Assessment Elements
- HomeworksTasks for the topics covered in class
- ExamThe oral exam includes the main topics covered in lectures and seminars.
Bibliography
Recommended Core Bibliography
- 9780262257053 - Sutton, Richard S.; Barto, Andrew G. - Reinforcement Learning : An Introduction - 1998 - A Bradford Book - http://search.ebscohost.com/login.aspx?direct=true&db=nlebk&AN=1094 - nlebk - 1094
- Li, Y. (2017). Deep Reinforcement Learning: An Overview. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.281A6E8D
Recommended Additional Bibliography
- Markov decision processes in practice, , 2017