Reinforcement Learning

Course Overview

This course introduces the fundamentals of reinforcement learning, a machine learning paradigm where an agent learns to make optimal decisions by interacting with an environment. Through theory and hands-on projects, students will understand key concepts and implement RL algorithms for real-world applications.

Learning Objectives

• ▸ Understand the fundamentals of Markov Decision Processes (MDPs)
• ▸ Implement and compare value-based and policy-based algorithms
• ▸ Apply RL techniques to optimization and control problems
• ▸ Analyze robustness and safety in RL systems

Topics Covered

• ▸ Markov Decision Processes and dynamic programming
• ▸ Temporal difference learning and Q-learning
• ▸ Policy gradient methods and actor-critic algorithms
• ▸ Deep reinforcement learning and neural networks
• ▸ Multi-agent and offline reinforcement learning
• ▸ Applications to optimization and control systems

Contact

For questions about this course, please contact: pegah.alizadeh@univ-lyon2.fr