Deep Reinforcement Learning 2.0
4.4 (449 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
4,476 students enrolled

Deep Reinforcement Learning 2.0

The smartest combination of Deep Q-Learning, Policy Gradient, Actor Critic, and DDPG
4.4 (449 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
4,476 students enrolled
Last updated 7/2020
English
English [Auto]
Current price: $139.99 Original price: $199.99 Discount: 30% off
5 hours left at this price!
30-Day Money-Back Guarantee
This course includes
  • 9.5 hours on-demand video
  • 7 articles
  • 1 downloadable resource
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
Training 5 or more people?

Get your team access to 4,000+ top Udemy courses anytime, anywhere.

Try Udemy for Business
What you'll learn
  • Q-Learning
  • Deep Q-Learning
  • Policy Gradient
  • Actor Critic
  • Deep Deterministic Policy Gradient (DDPG)
  • Twin-Delayed DDPG (TD3)
  • The Foundation Techniques of Deep Reinforcement Learning
  • How to implement a state of the art AI model that is over performing the most challenging virtual applications
Course content
Expand all 63 lectures 09:38:48
+ Part 1 - Fundamentals
11 lectures 53:31
Some resources before we start
00:37
BONUS: Learning Path
00:33
Deep Q-Learning
06:54
Actor-Critic
04:05
Taxonomy of AI models
07:48
BONUS: 5 Advantages of DRL
00:45
BONUS: RL Algorithms Map
00:32
Get the materials
00:04
+ Part 2 - Twin Delayed DDPG Theory
4 lectures 50:39
Introduction and Initialization
14:27
The Q-Learning part
18:42
The Policy Learning part
13:39
The whole training process
03:51
+ Part 3 - Twin Delayed DDPG Implementation
22 lectures 03:09:51
The whole code folder of the course with all the implementations
00:18
Beginning
05:36
Implementation - Step 1
15:46
Implementation - Step 2
15:12
Implementation - Step 3
13:55
Implementation - Step 4
14:09
Implementation - Step 5
11:03
Implementation - Step 6
09:43
Implementation - Step 7
04:26
Implementation - Step 8
07:44
Implementation - Step 9
03:55
Implementation - Step 10
04:08
Implementation - Step 11
07:33
Implementation - Step 12
04:06
Implementation - Step 13
05:31
Implementation - Step 14
06:54
Implementation - Step 15
14:20
Implementation - Step 16
08:54
Implementation - Step 17
06:11
Implementation - Step 18
13:30
Implementation - Step 19
11:46
Implementation - Step 20
05:11
+ The Final Demo!
2 lectures 27:57
Demo - Training
17:52
Demo - Inference
10:05
+ Annex 1 - Artificial Neural Networks
8 lectures 01:17:37
Plan of Attack
02:51
The Neuron
16:15
The Activation Function
08:29
How do Neural Networks Work?
12:47
How do Neural Networks Learn?
12:58
Gradient Descent
10:12
Stochastic Gradient Descent
08:44
Backpropagation
05:21
+ Annex 2 - Q-Learning
10 lectures 02:02:59
Plan of Attack
04:04
What is Reinforcement Learning?
11:26
The Bellman Equation
18:25
The Plan
02:12
Markov Decision Process
16:27
Policy vs Plan
12:55
Living Penalty
09:47
Q-Learning Intuition
14:45
Temporal Difference
19:27
Q-Learning Visualization
13:31
+ Annex 3 - Deep Q-Learning
5 lectures 55:46
Plan of Attack
02:17
Deep Q-Learning Intuition - Step 1
15:15
Deep Q-Learning Intuition - Step 2
06:06
Experience Replay
15:45
Action Selection Policies
16:23
+ Bonus Lectures
1 lecture 00:27
***YOUR SPECIAL BONUS***
00:27
Requirements
  • Some maths basics like knowing what is a differentiation or a gradient
  • A bit of programming knowledge (classes and objects)
Description

Welcome to Deep Reinforcement Learning 2.0!

In this course, we will learn and implement a new incredibly smart AI model, called the Twin-Delayed DDPG, which combines state of the art techniques in Artificial Intelligence including continuous Double Deep Q-Learning, Policy Gradient, and Actor Critic. The model is so strong that for the first time in our courses, we are able to solve the most challenging virtual AI applications (training an ant/spider and a half humanoid to walk and run across a field).

To approach this model the right way, we structured the course in three parts:

  • Part 1: Fundamentals
    In this part we will study all the fundamentals of Artificial Intelligence which will allow you to understand and master the AI of this course. These include Q-Learning, Deep Q-Learning, Policy Gradient, Actor-Critic and more.

  • Part 2: The Twin-Delayed DDPG Theory
    We will study in depth the whole theory behind the model. You will clearly see the whole construction and training process of the AI through a series of clear visualization slides. Not only will you learn the theory in details, but also you will shape up a strong intuition of how the AI learns and works. The fundamentals in Part 1, combined to the very detailed theory of Part 2, will make this highly advanced model accessible to you, and you will eventually be one of the very few people who can master this model.

  • Part 3: The Twin-Delayed DDPG Implementation
    We will implement the model from scratch, step by step, and through interactive sessions, a new feature of this course which will have you practice on many coding exercises while we implement the model. By doing them you will not follow passively the course but very actively, therefore allowing you to effectively improve your skills. And last but not least, we will do the whole implementation on Colaboratory, or Google Colab, which is a totally free and open source AI platform allowing you to code and train some AIs without having any packages to install on your machine. In other words, you can be 100% confident that you press the execute button, the AI will start to train and you will get the videos of the spider and humanoid running in the end.

Who this course is for:
  • Data Scientists who want to take their AI Skills to the next level
  • AI experts who want to expand on the field of applications
  • Engineers who work in technology and automation
  • Businessmen and companies who want to get ahead of the game
  • Students in tech-related programs who want to pursue a career in Data Science, Machine Learning, or Artificial Intelligence
  • Anyone passionate about Artificial Intelligence