Description

The course is crafted to reflect the in-demand skills in the marketplace that will help you in mastering the key concepts and methodologies of RL and deep RL, along with several practical implementations.
This course will help you know the theory and practical aspects of reinforcement and deep reinforcement learning.

Reinforcement learning is a subset of machine learning. In the RL training method, desired actions are rewarded, and undesired actions are punished. Deep RL is also a subfield of machine learning. In deep RL, intelligent machines and software are trained to learn from their actions in the same way that humans learn from experience. Deep RL has the capability to solve complex problems that were unmanageable by machines in the past. Therefore, the potential applications of deep RL in various sectors are enormous. We will start with an introduction to reinforcement learning and look at some case studies and real-world examples. Then you will look at Naïve/Random solutions and RL-based solutions. Next, you will see different types of RL solutions such as hyperparameters, Markov Decision Process, Q-Learning, and SARSA followed by a mini project on Frozen Lake. You will then learn deep learning/neural networks and deep RL/deep Q networks. Next, you will work on car racing and trading projects. Finally, you will go through some interview questions. By the end of this course, you will be able to relate the concepts and practical applications of reinforcement and deep reinforcement learning with real-world problems and implement any project that requires reinforcement and deep reinforcement learning knowledge from scratch. All the resource files are added to the GitHub repository at: https://github.com/PacktPublishing/Reinforcement-Learning-and-Deep-RL-Python-Theory-and-Projects-

What You Will Learn

Go through deep reinforcement learning applications
Learn Q-learning, SARSA, and random solutions using Python
Study deep learning fundamentals and hyper-parameters of deep RL
Make a Frozen Lake app using Python and a CIFAR project using PyTorch
Build Cart-Pole and Car Racing projects from scratch using Stable Baseline 3
Build Trading Bot RL and go through interview questions

Audience

This course is designed for beginners who know absolutely nothing about reinforcement and deep reinforcement learning, the ones who want to develop intelligent solutions, and the ones who want to learn the theoretical concepts first before implementing them using Python. An individual who wants to learn PySpark along with its implementation in realistic projects, machine learning or deep learning lovers, and anyone interested in artificial intelligence will be highly benefitted.
You would need prior knowledge of Python, an elementary understanding of programming, and a willingness to learn and practice.

Approach

In this comprehensive course, each new theoretical explanation is followed by practical implementation. This course offers you the right balance between theory and practice. The course curriculum includes six projects to simplify your learning. The explanations of all the theoretical concepts are clear and concise. The instructors lay special emphasis on complex theoretical concepts, making it easier for you to understand them.

Key Features

Learn from a comprehensive yet self-explanatory course, divided into 145+ videos along with detailed code notebooks * Structured course with solid basic understanding and advanced practical concepts * Up-to-date, practical explanations and live coding with Python to build six projects at an adequate pace

Github Repo

https://github.com/PacktPublishing/Reinforcement-Learning-and-Deep-RL-Python-Theory-and-Projects-

About the Author

AI Sciences

AI Sciences are experts, PhDs, and artificial intelligence practitioners, including computer science, machine learning, and Statistics. Some work in big companies such as Amazon, Google, Facebook, Microsoft, KPMG, BCG, and IBM. AI sciences produce a series of courses dedicated to beginners and newcomers on techniques and methods of machine learning, statistics, artificial intelligence, and data science. They aim to help those who wish to understand techniques more easily and start with less theory and less extended reading. Today, they publish more comprehensive courses on specific topics for wider audiences. Their courses have successfully helped more than 100,000 students master AI and data science.

Course Outline

1. Introduction to the Course

1. Introduction to Instructor

This video provides an introduction of the instructor.

2. Course Introduction

This video provides an extension and focus areas about this course in detail.

2. Motivation and Applications

1. What Is Reinforcement Learning

This video provides an overview about reinforcement learning.

2. What Is Reinforcement Learning Hiders and Seekers by OpenAI

This video explains about reinforcement learning hiders and seekers by OpenAI in the simplest way.

3. RL Versus Other ML Frameworks

This video demonstrates the difference between RL and other ML frameworks.

4. Why RL

This video explains why there is a need of reinforcement learning.

5. Examples of RL

This video explores some of the examples of RL.

6. Limitations of RL

This video explains the limitations of RL.

7. Exercises

This is an exercise video on reinforcement learning.

3. Terminologies of RL

1. Introduction

This video provides an introduction to the section.

2. Environment

This video talks about the environment.

3. Agent

This video explains the agent.

4. Action

This video explains the action items.

5. State

This video explains about the state.

6. Goal and Done State

This video explains the goal and done state.

7. Reward

This video talks about the reward.

8. Fun Activity

This video shows the fun activity.

9. Policy and Plan

This video demonstrates about the policy and plan.

10. Episode

This video talks about the episode.

4. Naive Random Solution

1. Introduction to Module

This video provides an introduction to the module.

2. Introduction to Game

This video provides an introduction to the game.

3. Rules of Game

This video explains the rules of the game.

4. Setting Up Game in Python - 1

This is the first of the three-part video that explains in setting up the game in Python.

5. Setting Up Game in Python - 2

This is the second of the three-part video that explains in setting up the game in Python.

6. Setting Up Game in Python - 3

This is the third of the three-part video that explains in setting up the game in Python.

7. Playing the Game Manually

This video demonstrates how to play the game manually.

8. Implementing Random Solution

This video explains implementing the Random solution.

9. Q-Learning and Q-Table Theory

This video explains about the Q-Learning and Q-Table theory.

10. Implementing Q-Learning - 1

This is the first of the three-part video that explains implementing Q-Learning.

11. Dry Run of Get State

This video explains the dry run of the get state.

12. Implementing Q Learning - 2

This is the second of the three-part video that explains implementing Q-Learning.

13. Implementing Q Learning - 3

This is the third of the three-part video that explains implementing Q-Learning.

14. Conclusion

This video concludes the section.

5. RL-Based Q-Learning

1. Introduction to Gym

This video provides an introduction to Gym.

2. Frozen Lake Rules

This video demonstrates the Frozen Lake rules.

3. Implementing Frozen Lake - 1

This is the first of the four-part video that explains implementing Frozen Lake.

4. Implementing Frozen Lake - 2

This is the second of the four-part video that explains implementing Frozen Lake.

5. Implementing Frozen Lake - 3

This is the third of the four-part video that explains implementing Frozen Lake.

6. Implementing Frozen Lake - 4

This is the fourth of the four-part video that explains implementing Frozen Lake.

7. Agent Plays the Game

This video demonstrates how the Agent plays the game.

8. Conclusion

This video concludes the section.

6. Hyper Parameters and Concepts

1. Introduction to Module

This video provides an introduction to the module.

2. Epsilon

This video explains about Epsilon.

3. Updating Epsilon Value

This video explains how to update Epsilon value.

4. Gamma and Discount Factor

This video talks about gamma and discount factor.

5. Alpha Learning Rate

This video explains about the Alpha learning rate.

6. Q-Learning Equation

This video explains about the Q-Learning equation.

7. Quiz (Number of Episodes)

This is a quiz video on number of episodes.

8. Solution (Number of Episodes)

This is a solution video on number of episodes.

9. Quiz (Alpha)

This is a quiz video on Alpha.

10. Solution (Alpha)

This is a solution video on Alpha.

7. SARSA (State-Action-Reward-State-Action)

1. Introduction to SARSA

This video provides an introduction to SARSA.

2. Off Policy Versus On Policy

This video differentiates between off policy and on policy.

3. SARSA Implementation

This video explains the implementation of SARSA.

4. SARSA Implementation update

This video explains the SARSA implementation update.

5. Pros and Cons

This video talks about the pros and cons of SARSA.

8. DNN Foundation for Deep RL

1. Why Deep Learning

This video explains why we need deep learning.

2. Why PyTorch

This video explains why we need PyTorch.

3. PyTorch Installation and Tensors Introduction

This video explains PyTorch installation and introduction to Tensors.

4. Automatic Differentiation PyTorch

This video explains automatic differentiation in PyTorch.

5. Why DNNs in Machine Learning

This video explains why we need DNNs in machine learning.

6. Representational Power and Data Utilization Capacity of DNN

This video explains about the representational power and data utilization capacity of DNN.

7. Perceptron

This video explains about Perceptron.

8. Perceptron Exercise

This is the exercise video on Perceptron.

9. Perceptron Exercise Solution

This is the exercise solution video on Perceptron.

10. Perceptron Implementation

This video explains the implementation of Perceptron.

11. DNN Architecture

This video explains about the DNN architecture.

12. DNN Architecture Exercise

This is an exercise video on DNN architecture.

13. DNN Architecture Exercise Solution

This is an exercise solution video on DNN architecture.

14. DNN ForwardStep Implementation

This video explains about the implementation of DNN ForwardStep.

15. DNN Why Activation Function Is Required

This video explains why activation function is required in DNN.

16. DNN Why Activation Function Is Required Exercise

This is an exercise video that explains why activation function is required.

17. DNN Why Activation Function Is Required Exercise Solution

This is an exercise solution video that explains why activation function is required.

18. MDP (Markov Decision Process)

This video explains about the MDP (Markov Decision Process).

19. DNN Properties of Activation Function

This video talks about the DNN properties of activation function.

20. DNN Activation Functions in PyTorch

This video demonstrates about the DNN activation functions in PyTorch.

21. DNN What Is Loss Function

This video demonstrates about the Loss function.

22. DNN What Is Loss Function Exercise

This is an exercise video on the Loss function in DNN.

23. DNN What Is Loss Function Exercise Solution

This is an exercise solution video on the Loss function in DNN.

24. DNN What Is Loss Function Exercise - 2

This is an exercise video on the Loss function in DNN.

25. DNN What Is Loss Function Exercise Solution - 2

This is an exercise solution video on the Loss function in DNN.

26. DNN Loss Function in PyTorch

This video explains about the Loss function in PyTorch.

27. DNN Gradient Descent

This video demonstrates about gradient descent.

28. DNN Gradient Descent Exercise

This is an exercise video on gradient descent.

29. DNN Gradient Descent Exercise Solution

This is an exercise solution video on gradient descent.

30. DNN Gradient Descent Implementation

This video explains about the implementation of gradient descent.

31. DNN Gradient Descent Stochastic Batch Minibatch

This video explains about the gradient descent Stochastic Batch Minibatch.

32. DNN Gradient Descent Summary

This is a summary video on gradient descent.

33. DNN Implementation Gradient Step

This video explains about the implementation of the gradient step.

34. DNN Implementation Stochastic Gradient Descent

This video explains about the implementation of stochastic gradient descent.

35. DNN Implementation Batch Gradient Descent

This video explains about the implementation of batch gradient descent.

36. DNN Implementation Minibatch Gradient Descent

This video explains about the implementation of minibatch gradient descent.

37. DNN Implementation in PyTorch

This video explains about the implementation in PyTorch.

38. DNN Weights Initializations

This video explains about weights initializations.

39. DNN Learning Rate

This video talks about the learning rate.

40. DNN Batch Normalization

This video explains about batch normalization.

41. DNN Batch Normalization Implementation

This video explains about the implementation of batch normalization.

42. DNN Optimizations

This video explains about DNN optimizations.

43. DNN Dropout

This video explains about the DNN Dropout.

44. DNN Dropout in PyTorch

This video explains about the DNN Dropout in PyTorch.

45. DNN Early Stopping

This video explains about DNN early stopping.

46. DNN Hyperparameters

This video explains about the DNN hyperparameters.

47. DNN PyTorch CIFAR10 Example

This video talks about the example of DNN PyTorch CIFAR10.

9. Deep RL DQN

1. Introduction and Recap

This video provides an introduction and recap to the section.

2. DQN Algorithm Steps

This video explains the steps of the DQN algorithm.

3. Introduction to Project (Cart pole)

This video provides an introduction to the project (cart pole).

4. Policy Network Explained

This video explains about the policy network.

5. Neural Network Class Implementation

This video explains about the implementation of the neural network class.

6. Replay Memory and Experience

This video talks about replay memory and experience.

7. Experience Implementation

This video demonstrates the implementation of Experience.

8. Replay Memory Implementation

This video demonstrates the implementation of replay memory.

9. Target Network and Recap

This video explains about the target network and recap.

10. Epsilon Greedy Strategy Implemented

This video explains the implementation of Epsilon Greedy Strategy.

11. Agent Class Implemented

This video explains about the implementation of the Agent class.

12. Environment Manager Implementation

This video explains about the implementation of the environment manager.

13. How to Get State

This video demonstrates how to get state.

14. Screen Pre-Processing

This video talks about screen pre-processing.

15. Screen Cropping

This video explains about screen cropping.

16. Screen Transformation

This video explains about screen transformation.

17. Processed Versus Non-Processed Screen

This video differentiates between processed and non-processed screen.

18. Moving Avg Implemented

This video explains the implementation of Moving Avg.

19. Plotting the Moving Avg

This video demonstrates plotting the Moving Avg.

20. Hyperparameter Initialization

This video demonstrates the initialization of hyperparameters.

21. Initializing the Classes

This video demonstrates the initializing of the classes.

22. Final Structure Implementation - 1

This is the first of the three-part video on the final structure implementation.

23. Extracting Tensors

This video explains how to extract tensors.

24. Final Structure Implementation - 2

This is the second of the three-part video on the final structure implementation.

25. Q-Values Calculator Implemented

This video explains about the implementation of the Q-values calculator.

26. Removing Errors Final Structure Implementation - 3

This is the third of the three-part video on removing errors final structure implementation.

27. Visualizing the Training

This video demonstrates visualizing the training.

10. Stable Baselines Cartpole Solution

1. Introduction to Stable Baseline

This video provides an introduction to Stable Baseline.

2. Loading and Understanding the Environment

This video explains about loading and understanding the environment.

3. Train RL Model

This video explains about training the RL model.

4. Evaluation and Testing

This video is on evaluation and testing.

5. Callbacks and Early Stopping

This video explains about callbacks and early stopping.

6. Changing Policy Architecture

This video explains about changing policy architecture.

7. Changing the Algorithm

This video talks about changing the algorithm.

8. Tips for Accuracy Improvement

This video demonstrates tips for accuracy improvement.

11. Trading Bot RL

1. Introduction to Libraries and Project

This video provides an introduction to libraries and the project.

2. Loading the Data

This video explains how to load the data.

3. Setting Up Environment

This video explains setting up the environment.

4. Random Actions

This video talks about random actions.

5. Training and Evaluating Model

This video explains training and evaluating the model.

12. Car Racing Game

1. Introduction to Game

This video provides an introduction to the game.

2. Importing the Dependencies

This video explains importing the dependencies.

3. Exploring the Environment

This video helps in exploring the environment.

4. Training and Testing the Model

This video demonstrates training and testing the model.

13. Interview Prep

1. Prep 1

This is the first of the two-part video that helps you with the preparation for the interview.

2. Prep 2

This is the second of the two-part video that helps you with the preparation for the interview.

Course Images

Reinforcement Learning and Deep RL Python (Theory and Projects)

By Packt

Booking options

Highlights

Description

Course Content

About The Provider

Tags

Reviews