If you want to learn reinforcement learning in depth, most online tutorials only teach how to use it, but you still don't understand the underlying principles after watching them. Academic papers are filled with complex mathematical formulas, which deters most people and makes systematic learning very difficult. I recently discovered this open-source book, "The Mathematical Foundations of Reinforcement Learning," which conveniently provides us with a clear path to understanding RL from a mathematical perspective. The algorithm uses the simplest "grid world" example throughout to explain the mathematical principles behind it in a clear and concise way. GitHub: https://t.co/WdQy1bI2Mp At the same time, the depth of the mathematics was well controlled to ensure that we could truly understand each knowledge point. It's beginner-friendly and also suitable for AI developers who want to gain a deeper understanding of RL principles. You can learn along with the accompanying videos.
