Deep Q-Learning/Deep Q-Network (DQN) Explained | Python Pytorch Deep Reinforcement Learning

preview_player
Показать описание
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.

Resources mentioned in video:

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
Рекомендации по теме
Комментарии
Автор

Please like and subscribe if this video is helpful for you 😀

johnnycode
Автор

The best teachers are those who teach a difficult lesson simply. thank you

zwpdioe
Автор

Johnny, you explained what I've been trying to wrap my head around for 9 months in a few minutes. Keep up the good work.

bagumamartin
Автор

Thank you for making this video. Your explanations were clear👍, and I learned a lot. Also, I find your voice very pleasant to listen to.

thefall
Автор

This was a really well explained example

johndowling
Автор

These videos on the new gymnasium version of gym are great. ❤ Could you do a video about thr bipedal walker environment?

johngrigoriadis
Автор

Thanks for this tutorial. It helped me to understand DQN .

rhbnzcq
Автор

You are a great teacher, thank you so much and Merry Christmas 2023

drm
Автор

Thanks again for your good work to help me understand reinforcement learning better.

kimiochang
Автор

thank you so much.can u please implement any env with dqn showing the forgetting problem?

koka-lfui
Автор

how to start learning reinforcement learning? i knew panda numpy matplotlib and basic ml algo?

DEVRAJ-npog
Автор

merci d'avoir dit moi comment crier l'environement en preier lieu, puisque je voudrais crier un environement tels que votre 4 x 4 mais avec d'autre images .

kskcqzd
Автор

Hey Johnny! Thanks so much for these videos! I have a question, is it possible to apply this algorithm to a continuous action space? For example, select a number in a range between [0, 120] as an action, or should I investigate other algorithms?

rickyolal
Автор

Thank you for making this video, may I ask a question about the Q network, why you set the input space for the network 16 input at 5:19 rather than 1 that represents the state index only?
I think 1 input is enough

nimo
Автор

sry, may i ask how can i find the max_step in the training of every epsiode? i do i know that max action is 200?

envelopepiano
Автор

Thanks for the video! Can you make a example with a BattleShips game? im trying, but the action (ex. position 12) its the same that the new state (12)😢

ProjectOfTheWeek
Автор

Great video, thanks. Please I am from cyber security background, please do you have idea on Network Attack Simulator (NASim) which also uses Deep Q-learning and openai gym? If you don't, please can you guide on where to find tutorials on it? I have checked youtube for weeks but couldn't get any. THANKS

AfitQADirectorate
Автор

I don't quite understand, because if you change the position of the puddles, the trained model will no longer be able to find the reward, right? What is the purpose of Qlearning then?

ProjectOfTheWeek
Автор

Any chance you can show us how to use Keras and RL on Tetris?

fernandomaroli
Автор

Just curious how you learned all of this? Did you just read the documentation or watch other videos?

codelock