index

📚 About This Repository

This repository contains notes and resources for studying the mathematical foundations of reinforcement learning. It is designed to complement the primary references and provide a structured approach to the material.

📚 Main References

• Mathematical Principles of Reinforcement Learning - Main course by Professor Zhao Shiyu
• Sutton & Barto - Reinforcement Learning: An Introduction - The definitive textbook

📖 Course Structure

• Fundamental tools
  • 01 Basic Concepts
  • 02 Bellman Equation
  • 03 Bellman Optimality Equation
• Algorithms/Methods
  • 04 Value Iteration & Policy Iteration
  • 05 Monte Carlo Methods
  • 06 Stochastic Approximation
  • 07 Temporal-Difference Methods
  • 08 Value Function Methods
  • 09 Policy Gradient Methods
  • 10 Actor-Critic Methods

🎯 Course Characteristics

Is this course suitable for you?

• Foundation vs. Program
• Math vs. Intuition
• Deep vs. Shallow understanding

---

Ready to begin? ⇒ 01 Basic Concepts

---

Philosophy: “Haste makes waste” - This course prioritizes solid foundations over speed. True mastery requires patience, proper time allocation, and step-by-step understanding.