This tutorial contains step by step explanation, code walkthru, and demo of how Deep Q-Learning (DQL) works. We'll use DQL to solve the very simple Gymnasium FrozenLake-v1 Reinforcement Learning environment. We'll cover the differences between Q-Learning vs DQL, the Epsilon-Greedy Policy, the Policy Deep Q-Network (DQN), the Target DQN, and Experience Replay. After this video, you will understand DQL.

Buy Me a Coffee: https://www.buymeacoffee.com/johnnycode
GitHub Repo: https://github.com/johnnycode8/gym_so...

Part 2 - Add Convolution Layers to DQN:    • Get Started with Convolutional Neural...  

Reinforcement Learning Playlist:    • Gymnasium (Deep) Reinforcement Learni...  

Resources mentioned in video:
How to Solve FrozenLake-v1 with Q-Learning:    • How to Use Q-Learning to Train Gymnas...  
Need help installing the Gymnasium library?    • Install Gymnasium (OpenAI Gym) on Win...  
Solve Neural Network in Python and by hand:    • How to Calculate Loss & Gradient Desc...  


00:00 Video Content
01:09 Frozen Lake Environment
02:16 Why Reinforcement Learning?
03:12 Epsilon-Greedy Policy
03:55 Q-Table vs Deep Q-Network
06:51 Training the Q-Table
10:10 Training the Deep Q-Network
14:49 Experience Replay
16:03 Deep Q-Learning Code Walkthru
29:49 Run Training Code & Demo