First of all, I can see why students prefer Udemy these days. The price is 3 times more expensive, but the lecture quality and explanation are very lacking. In particular, MDP/Dynamic/MonteCalo are seriously lacking in lecture quality and are worse than I thought. I majored in statistics, and I wanted to learn how to approach reinforcement in computer science through this lecture. I didn't want a lecture that simply threw out a few mathematical formulas and explained them, but that was my mistake. 

For reference, if you don't understand this lecture, I think it would be good to watch YouTube's "Mutual Information" to systematize mathematical formulas. 

If you want to apply it to real life, I think you can watch Udemy's step ahdead reinforcement learning. It uses Pytorch, but I think it would be more beneficial as a lecture related to code.

sd4beatles0681

The easiest and most detailed lecture on reinforcement learning, the core technology for business innovation!!!
We will put reinforcement learning in your hands within 17 days, dedicating 2 hours a day (2 lectures).
From now on, reinforcement learning will not be a difficult problem to understand, but a great tool for you.

multicoreit

AI 치트키위크 30% 깜짝 할인

Reinforcement Learning for Programmers (Author's Direct Lecture)

입문

초급

중급이상

Reinforcement Learning(RL)

Artificial Neural Network

Lecture introduction

Reinforcement learning concept

Basic reinforcement learning algorithm

Artificial intelligence concept

Function approximation

DQN algorithm

REINFORCE algorithm

A2C algorithm

PPO algorithm

Tuning artificial neural networks

Tuning reinforcement learning algorithms

Finish the course