Reinforcement Learning and Deep RL Python (Theory and Projects)

Preview this course

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.

Unlimited access to 750+ courses.
Enjoy a Free Trial. Cancel Anytime.

- OR -

30-Day Money-Back Guarantee
Full Lifetime Access.
156 on-demand videos & exercises
Level: Beginner
English
14hrs 16mins
Access on mobile, web and TV

What to know about this course

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-


Who's this course for?

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.


What you'll 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

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

Course Curriculum

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.