Deep Q Learning Networks

preview_player
Показать описание
Chief Data Scientist Jon Krohn explores deep reinforcement learning algorithms and demonstrates essential theory of deep reinforcement learning as well as DQNs.

Video course also available in Safari.
  1. LiveLessons
  2. Jon Krohn
  3. DQN
  4. Deep Learning
  5. Deep Q Learning Networks
  6. Data Science
Рекомендации по теме
Deep Q-Networks Explained! 0:10:51

Deep Q-Networks Explained!

Deep Q Learning 1:12:15

Deep Q Learning Networks

A friendly introduction 0:36:26

A friendly introduction to deep reinforcement learning, Q-networks and policy gradients

Deep Q-Learning - 0:10:50

Deep Q-Learning - Combining Neural Networks and Reinforcement Learning

Deep Reinforcement Learning: 0:21:15

Deep Reinforcement Learning: Neural Networks for Learning Control Laws

What is Q-Learning 0:45:44

What is Q-Learning (back to basics)

Deep Q-Learning/Deep Q-Network 0:34:05

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

Q Learning Explained 0:09:27

Q Learning Explained (tutorial)

Deep Learning 9/26/24 1:00:29

Deep Learning 9/26/24

Reinforcement Learning from 0:08:25

Reinforcement Learning from scratch

MIT 6.S091: Introduction 1:07:30

MIT 6.S091: Introduction to Deep Reinforcement Learning (Deep RL)

Deep Q Learning 0:38:55

Deep Q Learning is Simple with PyTorch | Full Tutorial 2020

Q-Learning Explained - 0:06:48

Q-Learning Explained - Reinforcement Learning Tutorial

Overview of Deep 0:24:50

Overview of Deep Reinforcement Learning Methods

Foundations of Artificial 0:17:27

Foundations of Artificial Neural Networks & Deep Q-Learning

MIT 6.S191 (2023): 0:57:33

MIT 6.S191 (2023): Reinforcement Learning

Deep Q-Network & 0:07:46

Deep Q-Network & Dueling network architectures for deep reinforcement learning

Deep Q Learning 0:32:19

Deep Q Learning w/ DQN - Reinforcement Learning p.5

CS885 Lecture 12: 0:28:11

CS885 Lecture 12: Deep Recurrent Q-Networks

Google DeepMind's Deep 0:01:43

Google DeepMind's Deep Q-learning playing Atari Breakout!

MIT 6.S191: Reinforcement 1:00:19

MIT 6.S191: Reinforcement Learning

Deep Q Learning 0:09:47

Deep Q Learning for Video Games - The Math of Intelligence #9

Deep Q-Networks (DQNs) 0:07:45

Deep Q-Networks (DQNs) in Reinforcement Learning

Deep Q-Learning using 0:09:14

Deep Q-Learning using Python - Part 1

Комментарии
Автор

spaceman, teacher, firefighter, postman, and now AI engineer.
you're a real man👏🏻

greatsaid
Автор

Hello Jon,
I am not finding the code in your Github.. can you please help me.
I will be thankful

ImtithalSaeed
Автор

Never knew Johnny Sins was into coding

thefrozenwaffle
Автор

Can’t believe u are such a multi faceted personality - A doctor, plumber, nurse, astronaut, firefighter, corporate guy, everything! And especially a guy who likes AI!

blackmane
Автор

When I run your notebook on my machine the training time is so much slower! You are able to do 1000 episodes in <30 seconds in the video but on my own machine it takes more like 45 minutes! Do you know what could cause this massive increase in runtime?

maxbird
Автор

excellent walkthrough of DQN theory. clear explanation with hands-on example!

chyldstudios
Автор

Everyone wants to be a datascientist even wwe wrestlers smh

DistortedV
Автор

I tried to run the code but failed with "ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (2, ) + inhomogeneous part." on "state = np.reshape(state, [1, state_size])", may I know why? Thank you very much!

xiaofengliu
Автор

54:52, doesn't predicting the values for the other actions and then feeding them into the fit function affect the optimizer?

andretelfer
Автор

At 50:50 we model the future reward by adding self.gamma * model prediction. My understanding is that the model predicts an action but not a reward. So how can we add the action the model suggests to the reward? Can you elaborate on this? Thank you very much

DanielWeikert
Автор

Thanks a million Sir,
Best tutorial for Deep Reinforcement Learning everrr!!

abdelrahmanshehata
Автор

Thank you for this excellent tutorial! Better than several others I watched and didn't find as helpful. The way you built things up theoretically and in code was extremely well organized, well explained, and easy to follow. Much appreciated!

mmartel
Автор

I came here to comment something about Johnny Sins but I see people have already did. 😂😂

saifahmadkhan
Автор

Correction: 1:08:20 openai-gym works also on windows, at least as of writing.

Phatency
Автор

1:04:10 We are still performing gradient descent, rather than gradient ascent, because we're using the Mean Squared Error loss function, between a target q-value prediction, and our current q-value prediction. Therefore the further away we are from this target, the larger the Mean Squared Error, and that distance is what the stochastic gradient descent is minimising.

cernsb
Автор

24:17 "...we are gonna reinforce ;)..." like a boss!

tonihuhtiniemi
Автор

My model isn't learning shit, lol

alexjjgreen
Автор

47, we have missions to do, what are you doing here?

ReelTikTube
Автор

After watching this video it seems like I have been taught RL by Johnny Sinns😂

vishalpramanik
Автор

The second chapter's title should be "Cart Pole", not "Cart Pool"!

BlackHermit