Course Overview
Welcome to Artificial Intelligence 2.0!
In this course, we will learn and implement a new incredibly smart AI model, called the Twin-Delayed DDPG or TD3, 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.
So are you ready to embrace AI at full power?
Come join us, never stop learning, and enjoy AI!
FAQ
FAQ area empty
Course curriculum
Chương 1 Part 1 - Fundamentals 9 bài · 51 phút
- Welcome Học thử 15:12
- Get the materials Học thử
- Prizes for Learning Học thử
- Some resources before we start Học thử
- Q-Learning Học thử 10:25
-
Deep Q-Learning 6:54
-
Policy Gradient 6:35
-
Actor-Critic 4:05
- Taxonomy of AI models Học thử 7:48
Chương 2 Part 2 - Twin Delayed DDPG Theory 4 bài · 51 phút
- Introduction and Initialization Học thử 14:27
-
The Q-Learning part 18:42
-
The Policy Learning part 13:39
-
The whole training process 3:51
Chương 3 Part 3 - Twin Delayed DDPG Implementation 22 bài · 3 giờ 10 phút
-
The whole code folder of the course with all the implementations
-
Beginning 5:36
-
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 9:43
-
Implementation - Step 7 4:26
-
Implementation - Step 8 7:44
-
Implementation - Step 9 3:55
-
Implementation - Step 10 4:08
-
Implementation - Step 11 7:33
-
Implementation - Step 12 4:06
-
Implementation - Step 13 5:31
-
Implementation - Step 14 6:54
-
Implementation - Step 15 14:20
-
Implementation - Step 16 8:54
-
Implementation - Step 17 6:11
-
Implementation - Step 18 13:30
-
Implementation - Step 19 11:46
-
Implementation - Step 20 5:11
Chương 4 The Final Demo! 2 bài · 28 phút
-
Demo - Training 17:52
-
Demo - Inference 10:05
Chương 5 Annex 1 - Artificial Neural Networks 8 bài · 1 giờ 18 phút
-
Plan of Attack 2:51
-
The Neuron 16:15
-
The Activation Function 8:29
-
How do Neural Networks Work? 12:47
-
How do Neural Networks Learn? 12:58
-
Gradient Descent 10:12
-
Stochastic Gradient Descent 8:44
-
Backpropagation 5:21
Chương 6 Annex 2 - Q-Learning 10 bài · 2 giờ 3 phút
-
Plan of Attack 4:04
-
What is Reinforcement Learning? 11:26
-
The Bellman Equation 18:25
-
The Plan 2:12
-
Markov Decision Process 16:27
-
Policy vs Plan 12:55
-
Living Penalty 9:47
-
Q-Learning Intuition 14:45
-
Temporal Difference 19:27
-
Q-Learning Visualization 13:31
Chương 7 Annex 3 - Deep Q-Learning 5 bài · 56 phút
-
Plan of Attack 2:17
-
Deep Q-Learning Intuition - Step 1 15:15
-
Deep Q-Learning Intuition - Step 2 6:06
-
Experience Replay 15:45
-
Action Selection Policies 16:23
Chương 8 Congratulations!! Don't forget your Prize :) 1 bài
-
Bonus Lecture
Requirment
-
Some maths basics like knowing what is a differentiation or a gradient
-
A bit of programming knowledge (classes and objects)
Outcomes
-
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
0 Student
5 Courses
0 review