Modern Reinforcement Learning: Deep Q Learning in PyTorch – Udemy

(10 customer reviews)




What you’ll learn

  • How to read and implement deep reinforcement learning papers
  • How to code Deep Q learning agents
  • How to Code Double Deep Q Learning Agents
  • How to Code Dueling Deep Q and Dueling Double Deep Q Learning Agents
  • How to write modular and extensible deep reinforcement learning software
  • How to automate hyperparameter tuning with command line arguments

In this complete deep reinforcement learning course you will learn a repeatable framework for reading and implementing deep reinforcement learning research papers. You will read the original papers that introduced the Deep Q learning, Double Deep Q learning, and Dueling Deep Q learning algorithms. You will then learn how to implement these in pythonic and concise PyTorch code, that can be extended to include any future deep Q learning algorithms. These algorithms will be used to solve a variety of environments from the Open AI gym’s Atari library, including Pong, Breakout, and Bankheist.

You will learn the key to making these Deep Q Learning algorithms work, which is how to modify the Open AI Gym’s Atari library to meet the specifications of the original Deep Q Learning papers. You will learn how to:

  • Repeat actions to reduce computational overhead

  • Rescale the Atari screen images to increase efficiency

  • Stack frames to give the Deep Q agent a sense of motion

  • Evaluate the Deep Q agent’s performance with random no-ops to deal with model over training

  • Clip rewards to enable the Deep Q learning agent to generalize across Atari games with different score scales

If you do not have prior experience in reinforcement or deep reinforcement learning, that’s no problem. Included in the course is a complete and concise course on the fundamentals of reinforcement learning. The introductory course in reinforcement learning will be taught in the context of solving the Frozen Lake environment from the Open AI Gym.

We will cover:

  • Markov decision processes

  • Temporal difference learning

  • The original Q learning algorithm

  • How to solve the Bellman equation

  • Value functions and action value functions

  • Model free vs. model based reinforcement learning

  • Solutions to the explore-exploit dilemma, including optimistic initial values and epsilon-greedy action selection

Also included is a mini course in deep learning using the PyTorch framework. This is geared for students who are familiar with the basic concepts of deep learning, but not the specifics, or those who are comfortable with deep learning in another framework, such as Tensorflow or Keras. You will learn how to code a deep neural network in Pytorch as well as how convolutional neural networks function. This will be put to use in implementing a naive Deep Q learning agent to solve the Cartpole problem from the Open AI gym. 

Who this course is for:

  • Python developers eager to learn about cutting edge deep reinforcement learning

Course content

  • Introduction
  • Fundamentals of Reinforcement Learning
  • Deep Learning Crash Course
  • Human Level Control Through Deep Reinforcement Learning: From Paper to Code
  • Deep Reinforcement Learning with Double Q Learning
  • Dueling Network Architectures for Deep Reinforcement Learning
  • Improving On Our Solutions
  • Conclusion
  • Bonus Lecture

10 reviews for Modern Reinforcement Learning: Deep Q Learning in PyTorch – Udemy

  1. Donny Phan

    Super practical. Lessons are catered towards anyone looking to find work in this industry. It felt very comprehensive and gave me a broad understanding of the programming spectrum

  2. Madhav raj Verma

    Thanks for your great effort. i am fully satisfied with this course the way you teach and your explanation are very clear ,The content you provide in your course no one can do this at this price.

  3. Sachin Gupta

    I really didn’t want to leave a low rating as Angela is a great teacher. The 1st half of this course was terrific. The 2nd half was terrible. Under the justification of “teaching students how to figure things out on their own”, pretty much all videos and all explanations were dropped. You were just told what to do, given links to documentation and told to figure it out on your own. I understand doing that to some degree, but to revert to that entirely for nearly half the content barely makes this a course. It’s just a list of things for you to learn, then you’re left on your own to learn them. The 2nd half was so bad, especially the data science component, that I didn’t bother finishing the course.

  4. Vincent Beaudet

    Amazing 40 days course.
    Angela is a great teacher.
    The other 60 days are all about web developement, interacting with web pages, on your own with little to no explanations. I did not expect that at all. I wanted to learn more about software and scripting.
    This left me disappointed , confused and i started to doubt myself. Not a fun experience after the amount of effort i’v put in this course.

    Exercices format and explanations for the first 40 days were worth it tho.

  5. Ben K

    Not just an introduction to python, but really helps you learn fundamental aspects of python and coding in general. Some parts may require some knowledge on the subject (data science comes to mind) and there is quite some web development in the course. So, a few areas were not completely to my liking (I would have liked to see it done differently), but this course deserves the 5 stars in my opinion.

  6. Omid Alikhel

    I found the method a bit difficult when a code is written and then changed back to something different, with no enough explanation of how something happened and where it came from or a step by step explanation of why something is happening, i have no doubt in the instructors talent, but we are beginners!

  7. Devang Jain

    The course is not updated and most of the solution codes don’t work and there are no video solutions towards the end

  8. Szymon Kozak

    I think that the course tutor is really good in giving right information to learn at the right time. Thanks to this fact, my understanding of coding in python after 29 days of learning is above my expectations.

  9. Begoña Ruiz Diaz

    Ha sido la mejor elección que podría haber hecho.

  10. Vaibhav Sachdeva

    I want to thank Angela for making such an amazing course. It really helped me explore more things with python.

Add a review

Your email address will not be published.