Practical AI with Python and Reinforcement Learning

About Course

Learn how to build and create intelligent agents with Practical AI with Python and Reinforcement Learning, a free online course available on Theetay. This course, offered by Udemy, teaches you how to use Python to harness the power of Neural Networks and Reinforcement Learning.

This course focuses on a practical approach that puts you in the driver’s seat to build and create intelligent agents, instead of just showing you small toy examples. Here we focus on giving you the power to apply artificial intelligence to your own problems, environments, and situations.

This course covers the following topics:

Artificial Neural Networks
Convolution Neural Networks
Classical Q-Learning
Deep Q-Learning
SARSA
Cross Entropy Methods
Double DQN
and much more!

This course is designed to help you create your own deep reinforcement learning agents on your own environments. It focuses on a practical approach with the right balance of theory and intuition with useable code. The course uses clear examples in slides to connect mathematical equations to practical code implementation, before showing how to manually implement the equations that conduct reinforcement learning.

You’ll learn how Deep Learning with Keras and TensorFlow works, before diving into Reinforcement Learning concepts, such as Q-Learning. Then we can combine these ideas to walk you through Deep Reinforcement Learning agents, such as Deep Q-Networks!

Enroll in this free course today and start building your own intelligent agents!

Reinforcement Learning with Python
Creating Artificial Neural Networks with TensorFlow
Using TensorFlow to create Convolution Neural Networks for Images
Using OpenAI to work with built-in game environments
Using OpenAI to create your own environments for any problem
Create Artificially Intelligent Agents
Tabular Q-Learning
State–action–reward–state–action (SARSA)
Deep Q-Learning (DQN)
DQN using Convolutional Neural Networks
Cross Entropy Method for Reinforcement Learning
Double DQN
Dueling DQN

Course Content

Course Overview

A Message from the Professor
– Course Curriculum Overview

09:34
– Course Success and Overview

06:44
Course Material Download Link

00:00

Course SetUp and Installation Procedures

Numpy Basics Overview

Matplotlib and Visualization Overview

– Introduction to Matplotlib

04:06
– Matplotlib Basics

12:35
– Matplotlib Understanding the Figure Object

07:32
– Matplotlib Implementing Figures and Axes

14:31
– Matplotlib Figure Parameters

04:56
– Matplotlib Subplots Functionality

19:17
– Matplotlib Styling Legends

07:02
– Matplotlib Styling Colors and Styles

14:29
– Advanced Matplotlib Commands Optional

03:52
– Matplotlib Exercise Questions Overview

06:10
– Matplotlib Exercise Questions Solutions

16:39

Machine Learning Deep Learning and Reinforcement Learning

Pandas and ScikitLearn Crash Course

Artificial Neural Network and TensorFlow Basics

– Introduction to Artificial Neural Networks

02:15
– Perceptron Model

10:39
– Neural Networks

07:19
– Activation Functions

10:39
– MultiClass Classification Considerations

10:34
– Cost Functions and Gradient Descent

18:13
– Backpropagation

14:47
– TensorFlow vs Keras Explained

02:13
– Keras Syntax Preparing the Data

10:49
– Keras Syntax Creating and Training the Model

13:59
– Keras Syntax Model Evaluation

12:56
– Keras Regression Exploratory Data Analysis

18:51
– Keras Regression EDA Continued

13:16
– Keras Regression Data Preprocessing and Model Creation

08:43
– Keras Regression Model Evaluation and Predictions

11:23
– Keras Classification EDA and Preprocessing

08:05
– Keras Classification Overfitting and Evaluation

16:50
– Keras Classification Overview of Project Options

01:40
– Keras Project Notebook Exercise Overview

07:41
– Keras Project Solution Exploratoy Data Analysis

20:35
– Keras Project Solutions Missing Data Part One

14:46
– Keras Project Solutions Dealing with Missing Data Part Two

12:02
– Keras Project Solutions Categorical Data

17:23
– Keras Project Solutions Data Preprocessing

03:45
– Keras Project Solutions Creating and Training the Model

03:57
– Keras Project Solutions Model Evaluation

09:42
– Tensorboard

18:22

Convolutional Neural Networks with TensorFlow

– Convolutional Neural Networks Section Overview

01:33
– Image Filters and Kernels

11:35
– Convolutional Layers

14:01
– Pooling Layers

06:47
– MNIST Data Set Overview

04:41
– CNN on MNIST The Data

12:57
– CNN on MNIST Creating and Training the Model

16:14
– CNN on MNIST Model Evaluation

06:53
– CNN on CIFAR10 The Data

11:24
– CNN on CIFAR10 Evaluating the Model

07:05
– Downloading Data Set for Real Image Lectures

05:22
– CNN on Real Image Files Reading in the Data

14:54
– CNN on Real Image Files Data Generation

15:37
– CNN on Real Image Files Creating the Model

13:37
– CNN on Real Image Files Model Evaluation

08:49
– CNN Exercise Project Overview

02:10
– CNN Exercise Project Solutions

08:31

Reinforcement Learning Core Concepts

Open AI Gym Overview

Classical Q Learning

– Introduction to Classical QLearning Overview

04:12
– History of QLearning

03:53
– QLearning Theory Part One Table Intuition

15:38
– QLearning Theory Part Two Q Target Equation

12:08
– QLearning Theory Part Three QUpdate Equation

08:28
– QLearning Theory Part Four Programmatic Q Updates

10:56
– QLearning Implementation Part One Environment Setup

14:15
– QLearning Implementation Part Two Table and Hyperparameters

10:34
– QLearning Implementation Part Three Update Functions

17:10
– QLearning Implementation Part Four Agent Training

17:03
– QLearning Implementation Part Five Visualization and Utilization

09:50
– Continuous QLearning Theory Part One Environment Setup

12:33
– Continuous QLearning Theory Part Two QTable Shape

16:33
– Continuous QLearning Part Four Discretization Implementation

17:38
– Continuous QLearning Part Five Functions and Hyperparameters

10:08
– Continuous QLearning Part Six Training and Usage

19:36
– QLearning Exercise Project

07:06
– QLearning Exercise Project Solutions

20:52

Deep QLearning

– DQN Section Overview

01:57
– History of DQN

04:45
– DQN Theory and Intuition Part One Review of Core RL Ideas

04:48
– DQN Theory and Intuition Part Two Neural Networks for RL

10:50
– DQN Theory and Intuition Part Three Feedback and Function Approximation

21:10
– DQN Theory and Intuition Part Four Experience Replay

18:46
– DQN Theory and Intuition Part Five Mapping Key Ideas to Code

16:04
– DQN Manual Implementation Part One Imports and Environment

04:45
– DQN Manual Implementation Part Two Artificial Neural Network

07:16
– DQN Manual Implementation Part Three Hyperparameters and Functions

18:43
– DQN Manual Implementation Part Four Model Training

15:51
– DQN KerasRL2 Part One Overview

07:20
– DQN KerasRL2 Part Two Imports and Environment

03:26
– DQN KerasRL2 Part Three Creating the ANN

05:40
– DQN KerasRL2 Part Four DQN Agent

13:43
– DQN Exercise Overview

03:28
– DQN Exercise Solutions

10:07

Deep QLearning on Images

– Introduction to Deep QLearning on Images

04:44
– Key Image Concepts Review

07:00
– Image History in Replay Buffer Concept Review

06:26
– Processing Images Part Three Coding Replay Buffer and Sequences

14:22
– Processing Images Part Four Coding Preprocessing

12:08
– DQN on Images Part One Imports and Processing

18:31
– DQN on Images Part Two Constructing the Network

12:00
– DQN on Images Part Three Setting up the Agent

19:25
– DQN Exercises Overview

06:05
– DQN Exercises Solution

20:05

Creating Custom OpenAI Gym Environments

– Introduction to Custom OpenAI Gym Environments

02:53
– Custom Gym Environments Class Structure Overview

08:35
– Creating Custom Game Part One Snake Game Overview

04:08
– Creating Custom Game Part two Class Structure and Setup

07:25
– Creating Custom Game Part Three Game Reset

06:58
– Creating Custom Game Part Four Direction and Movement

07:55
– Creating Custom Game Part Five Eating and Spawning Food

03:57
– Creating Custom Game Part Six Human Input

07:12
– Creating Custom Game Part Seven Displaying Score

04:32
– Creating Custom Game Part Eight Game Over Conditions

03:38
– Creating Custom Game Part Nine Ending the Game

03:18
– Creating Custom Game Part Ten Play Logic

16:35
– OpenAI Gym Environment Directory Structure Overview

05:57
– Gym Directory and Setup File

07:06
– Filling in the initpy Files

04:27
– Conversion of Game to OpenAI Gym Environment Class

25:15
– Conversion of Game to OpenAI Gym Environment Part Two

14:34
– Registration of the Environment

09:24
– Training an Agent on the Custom Environment

07:51
– Training an Agent on the Custom Environment

07:51

Add this certificate to your resume to demonstrate your skills & increase your chances of getting noticed.

Student Ratings & Reviews

No Review Yet

About Course

What Will You Learn?

Course Content

Course Overview

A Message from the Professor

– Course Curriculum Overview

– Course Success and Overview

Course Material Download Link

Course SetUp and Installation Procedures

– Anaconda and Jupyter Notebook Install and Setup

– Environment Setup Walkthrough

Numpy Basics Overview

– Introduction to Numpy Section

– NumPy Arrays

– Numpy Operations Part One

– Numpy Operations Part Two

– Numpy Exercise Overview

– Numpy Exercise Solutions

Matplotlib and Visualization Overview

– Introduction to Matplotlib

– Matplotlib Basics

– Matplotlib Understanding the Figure Object

– Matplotlib Implementing Figures and Axes

– Matplotlib Figure Parameters

– Matplotlib Subplots Functionality

– Matplotlib Styling Legends

– Matplotlib Styling Colors and Styles

– Advanced Matplotlib Commands Optional

– Matplotlib Exercise Questions Overview

– Matplotlib Exercise Questions Solutions

Machine Learning Deep Learning and Reinforcement Learning

– What is Machine Learning Deep Learning and Artificial Intelligence

– Supervised Machine Learning Process

Pandas and ScikitLearn Crash Course

– Pandas Series Part One

– Pandas Series Part Two

– Pandas DataFrames Part One

– Pandas DataFrames Part Two

– Pandas DataFrames Part Three

– Pandas DataFrames Part Four

– ScikitLearn Using TrainTestSplit

– ScikitLearn Using Metrics

Artificial Neural Network and TensorFlow Basics

– Introduction to Artificial Neural Networks

– Perceptron Model

– Neural Networks

– Activation Functions

– MultiClass Classification Considerations

– Cost Functions and Gradient Descent

– Backpropagation

– TensorFlow vs Keras Explained

– Keras Syntax Preparing the Data

– Keras Syntax Creating and Training the Model

– Keras Syntax Model Evaluation

– Keras Regression Exploratory Data Analysis

– Keras Regression EDA Continued

– Keras Regression Data Preprocessing and Model Creation

– Keras Regression Model Evaluation and Predictions

– Keras Classification EDA and Preprocessing

– Keras Classification Overfitting and Evaluation

– Keras Classification Overview of Project Options

– Keras Project Notebook Exercise Overview

– Keras Project Solution Exploratoy Data Analysis

– Keras Project Solutions Missing Data Part One

– Keras Project Solutions Dealing with Missing Data Part Two

– Keras Project Solutions Categorical Data

– Keras Project Solutions Data Preprocessing

– Keras Project Solutions Creating and Training the Model

– Keras Project Solutions Model Evaluation

– Tensorboard

Convolutional Neural Networks with TensorFlow

– Convolutional Neural Networks Section Overview

– Image Filters and Kernels

– Convolutional Layers

– Pooling Layers

– MNIST Data Set Overview

– CNN on MNIST The Data

– CNN on MNIST Creating and Training the Model

– CNN on MNIST Model Evaluation

– CNN on CIFAR10 The Data