Reinforcement learning
Practical AI with Python and Reinforcement Learning
Explore Python tools and reinforcement learning techniques for building AI programs.
A small sample of 30,000+ courses curated from around the world, all available to DoJo members.
A free 30-minute conversation with Ted about your goals.
Already a member? Open this course (opens in a new tab)
Course topics
Reinforcement learning
- Neural networks
- Q-learning
- Custom environments
You observe the behaviour
Find your fit
Is this a useful starting point?
For Python developers with machine-learning basics; this is not a beginner course.
- Starting point
- Expert
- Course length
- 26.5 total hours
- Lessons
- 156 lectures
Course by Jose Portilla, Pierian Training
Course last updated: 04/2023
Requirements
- You should be very comfortable with basic Python and installing Python libraries.
- This is NOT a course for beginners, we highly suggest you take our "Data Science and Machine Learning Masterclass" first!
What is included
- 26.5 hours on-demand video
- 6 articles
- 9 downloadable resources
- Access on mobile
- Certificate of completion
DoJo membership: A$250 per month per seat, excluding GST. Includes fortnightly group support and a private member community.
Explore the lessons
Course curriculum.
14 sections • 156 lectures • 26h 24m total length
Course Overview3 lectures • 17min
- Welcome Message00:37
- Course Curriculum Overview09:34
- Course Success and Overview06:44
- Check In Quiz 3 questions
Course Set-Up and Installation Procedures3 lectures • 24min
- Anaconda and Jupyter Notebook Install and Setup13:49
- Note on Environment Setup00:27
- Environment Setup Walkthrough10:09
Numpy Basics Overview6 lectures • 53min
- Introduction to Numpy Section02:14
- NumPy Arrays22:41
- Numpy Operations - Part One11:06
- Numpy Operations - Part Two08:14
- Numpy Exercise Overview01:18
- Numpy Exercise Solutions07:05
Matplotlib and Visualization Overview11 lectures • 1hr 51min
- Introduction to Matplotlib04:06
- Matplotlib Basics12:35
- Matplotlib - Understanding the Figure Object07:32
- Matplotlib - Implementing Figures and Axes14:31
- Matplotlib - Figure Parameters04:56
- Matplotlib - Subplots Functionality19:17
- Matplotlib Styling - Legends07:02
- Matplotlib Styling - Colors and Styles14:29
- Advanced Matplotlib Commands (Optional)03:52
- Matplotlib Exercise Questions Overview06:10
- Matplotlib Exercise Questions - Solutions16:39
Machine Learning, Deep Learning, and Reinforcement Learning2 lectures • 25min
- What is Machine Learning, Deep Learning, and Artificial Intelligence?11:08
- Supervised Machine Learning Process13:41
Pandas and Scikit-Learn Crash Course9 lectures • 1hr 43min
- Pandas and Scikit-Learn Overview00:09
- Pandas - Series Part One09:28
- Pandas - Series Part Two10:41
- Pandas - DataFrames - Part One19:27
- Pandas - DataFrames - Part Two08:18
- Pandas - DataFrames - Part Three13:57
- Pandas - DataFrames - Part Four14:30
- Scikit-Learn - Using Train-Test-Split11:20
- Scikit-Learn - Using Metrics14:48
Artificial Neural Network and TensorFlow Basics27 lectures • 5hr 1min
- Introduction to Artificial Neural Networks02:15
- Perceptron Model10:39
- Neural Networks07:19
- Activation Functions10:39
- Multi-Class Classification Considerations10:34
- Cost Functions and Gradient Descent18:13
- Backpropagation14:47
- TensorFlow vs. Keras Explained02:13
- Keras Syntax - Preparing the Data10:49
- Keras Syntax - Creating and Training the Model13:59
- Keras Syntax - Model Evaluation12:56
- Keras Regression - Exploratory Data Analysis18:50
- Keras Regression - EDA Continued13:15
- Keras Regression - Data Preprocessing and Model Creation08:42
- Keras Regression - Model Evaluation and Predictions11:23
- Keras Classification - EDA and Preprocessing08:05
- Keras Classification - Overfitting and Evaluation16:50
- Keras Classification - Overview of Project Options01:40
- Keras Project Notebook Exercise Overview07:41
- Keras Project Solution - Exploratoy Data Analysis20:35
- Keras Project Solutions - Missing Data - Part One14:46
- Keras Project Solutions - Dealing with Missing Data - Part Two12:02
- Keras Project Solutions - Categorical Data17:23
- Keras Project Solutions - Data Preprocessing03:45
- Keras Project Solutions- Creating and Training the Model03:57
- Keras Project Solutions - Model Evaluation09:42
- Tensorboard18:22
Convolutional Neural Networks with TensorFlow17 lectures • 2hr 42min
- Convolutional Neural Networks Section Overview01:33
- Image Filters and Kernels11:35
- Convolutional Layers14:01
- Pooling Layers06:47
- MNIST Data Set Overview04:41
- CNN on MNIST - The Data12:57
- CNN on MNIST - Creating and Training the Model16:14
- CNN on MNIST - Model Evaluation06:53
- CNN on CIFAR-10 - The Data11:23
- CNN on CIFAR-10 - Evaluating the Model07:05
- Downloading Data Set for Real Image Lectures05:22
- CNN on Real Image Files - Reading in the Data14:54
- CNN on Real Image Files - Data Generation15:37
- CNN on Real Image Files - Creating the Model13:37
- CNN on Real Image Files - Model Evaluation08:49
- CNN Exercise Project Overview02:10
- CNN Exercise Project Solutions08:31
Reinforcement Learning - Core Concepts5 lectures • 32min
- Overview of Core Concepts for Reinforcement Learning Section01:37
- Agents, Environments, and Policy11:43
- Rewards, Discount Factors, and Bellman Equation13:35
- Deterministic vs. Stochastic Processes05:17
- Tabular Reinforcement Learning00:08
Open AI Gym Overview6 lectures • 1hr 21min
- Introduction to OpenAI Gym Section01:04
- OpenAI Overview and History11:40
- OpenAI Gym - Documentation Tour12:38
- OpenAI Gym - Environment Key Ideas07:51
- OpenAI Gym - Working with the Environment27:23
- OpenAI Gym - Agent Interacting with the Environment20:30
Classical Q Learning19 lectures • 3hr 53min
- Introduction to Classical Q-Learning Overview04:12
- History of Q-Learning03:53
- Q-Learning Theory - Part One - Table Intuition15:38
- Q-Learning Theory - Part Two - Q Target Equation12:08
- Q-Learning Theory - Part Three - Q-Update Equation08:28
- Q-Learning Theory - Part Four - Programmatic Q Updates10:56
- Q-Learning Implementation - Part One - Environment Setup14:15
- Q-Learning Implementation - Part Two - Table and Hyperparameters10:34
- Q-Learning Implementation - Part Three - Update Functions17:10
- Q-Learning Implementation - Part Four - Agent Training17:03
- Q-Learning Implementation - Part Five - Visualization and Utilization09:50
- Continuous Q-Learning Theory - Part One - Environment Setup12:33
- Continuous Q-Learning Theory - Part Two- Q-Table Shape16:33
- Continuous Q-Learning Theory - Part Three - Discretization Theory04:57
- Continuous Q-Learning - Part Four - Discretization Implementation17:38
- Continuous Q-Learning - Part Five - Functions and Hyperparameters10:08
- Continuous Q-Learning - Part Six - Training and Usage19:35
- Q-Learning Exercise Project07:06
- Q-Learning Exercise Project - Solutions20:51
Deep Q-Learning17 lectures • 2hr 49min
- DQN Section Overview01:57
- History of DQN04:45
- DQN Theory and Intuition - Part One - Review of Core RL Ideas04:48
- DQN Theory and Intuition - Part Two - Neural Networks for RL10:50
- DQN Theory and Intuition - Part Three - Feedback and Function Approximation21:10
- DQN Theory and Intuition - Part Four - Experience Replay18:46
- DQN Theory and Intuition - Part Five - Mapping Key Ideas to Code16:04
- DQN Manual Implementation - Part One - Imports and Environment04:44
- DQN Manual Implementation - Part Two - Artificial Neural Network07:16
- DQN Manual Implementation - Part Three - Hyperparameters and Functions18:43
- DQN Manual Implementation - Part Four - Model Training15:51
- DQN - Keras-RL2 - Part One - Overview07:20
- DQN - Keras-RL2 - Part Two - Imports and Environment03:26
- DQN - Keras-RL2 - Part Three - Creating the ANN05:40
- DQN - Keras-RL2 - Part Four - DQN Agent13:43
- DQN - Exercise Overview03:28
- DQN - Exercise Solutions10:07
Deep Q-Learning on Images11 lectures • 2hr 1min
- Introduction to Deep Q-Learning on Images04:44
- Files for DQN on Images00:02
- Key Image Concepts Review07:00
- Image History in Replay Buffer - Concept Review06:25
- Processing Images Part Three- Coding Replay Buffer and Sequences14:22
- Processing Images Part Four - Coding Preprocessing12:08
- DQN on Images - Part One - Imports and Processing18:31
- DQN on Images - Part Two - Constructing the Network12:00
- DQN on Images - Part Three - Setting up the Agent19:25
- DQN Exercises Overview06:05
- DQN Exercises Solution20:05
Creating Custom OpenAI Gym Environments20 lectures • 2hr 32min
- Introduction to Custom OpenAI Gym Environments02:53
- Custom Gym Environments - Class Structure Overview08:35
- Creating Custom Game - Part One - Snake Game Overview04:08
- Creating Custom Game - Part two - Class Structure and Setup07:25
- Creating Custom Game - Part Three - Game Reset06:58
- Creating Custom Game - Part Four - Direction and Movement07:55
- Creating Custom Game - Part Five - Eating and Spawning Food03:57
- Creating Custom Game - Part Six - Human Input07:12
- Creating Custom Game - Part Seven - Displaying Score04:31
- Creating Custom Game - Part Eight - Game Over Conditions03:38
- Creating Custom Game - Part Nine - Ending the Game03:18
- Creating Custom Game - Part Ten - Play Logic16:35
- Important Note on __init__.py Files00:34
- OpenAI Gym Environment - Directory Structure Overview05:57
- Gym Directory and Setup File07:06
- Filling in the __init__.py Files04:27
- Conversion of Game to OpenAI Gym Environment Class25:15
- Conversion of Game to OpenAI Gym Environment - Part Two14:34
- Registration of the Environment09:23
- Training an Agent on the Custom Environment07:51
From learning to practice
Try this next.
Run a small reinforcement-learning exercise and compare the agent's behaviour across repeatable conditions.
A useful next step
Choose where to start.
Talk through your goals in a free 30-minute discovery call with Ted. Bring a task you want to improve and the tools you already use.
Book a discovery callExplore DoJo membership