What do you think?
Rate this book
Grokking Deep Reinforcement Learning
Grokking Deep Reinforcement Learning uses engaging exercises to teach you how to build deep learning systems. This book combines annotated Python code with intuitive explanations to explore DRL techniques. You’ll see how algorithms function and learn to develop your own DRL agents using evaluative feedback.
Summary
We all learn through trial and error. We avoid the things that cause us to experience pain and failure. We embrace and build on the things that give us reward and success. This common pattern is the foundation of deep reinforcement learning: building machine learning systems that explore and learn based on the responses of the environment. Grokking Deep Reinforcement Learning introduces this powerful machine learning approach, using examples, illustrations, exercises, and crystal-clear teaching. You'll love the perfectly paced teaching and the clever, engaging writing style as you dig into this awesome exploration of reinforcement learning fundamentals, effective deep learning techniques, and practical applications in this emerging field.
Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.
About the technology
We learn by interacting with our environment, and the rewards or punishments we experience guide our future behavior. Deep reinforcement learning brings that same natural process to artificial intelligence, analyzing results to uncover the most efficient ways forward. DRL agents can improve marketing campaigns, predict stock performance, and beat grand masters in Go and chess.
About the book
Grokking Deep Reinforcement Learning uses engaging exercises to teach you how to build deep learning systems. This book combines annotated Python code with intuitive explanations to explore DRL techniques. You’ll see how algorithms function and learn to develop your own DRL agents using evaluative feedback.
What's inside
ÌýÌýÌý An introduction to reinforcement learning
ÌýÌýÌý DRL agents with human-like behaviors
ÌýÌýÌý Applying DRL to complex situations
About the reader
For developers with basic deep learning experience.
About the author
Miguel Morales works on reinforcement learning at Lockheed Martin and is an instructor for the Georgia Institute of Technology’s Reinforcement Learning and Decision Making course.
Table of Contents
1 Introduction to deep reinforcement learning
2 Mathematical foundations of reinforcement learning
3 Balancing immediate and long-term goals
4 Balancing the gathering and use of information
5 Evaluating agents� behaviors
6 Improving agents� behaviors
7 Achieving goals more effectively and efficiently
8 Introduction to value-based deep reinforcement learning
9 More stable value-based methods
10 Sample-efficient value-based methods
11 Policy-gradient and actor-critic methods
12 Advanced actor-critic methods
13 Toward artificial general intelligence
Summary
We all learn through trial and error. We avoid the things that cause us to experience pain and failure. We embrace and build on the things that give us reward and success. This common pattern is the foundation of deep reinforcement learning: building machine learning systems that explore and learn based on the responses of the environment. Grokking Deep Reinforcement Learning introduces this powerful machine learning approach, using examples, illustrations, exercises, and crystal-clear teaching. You'll love the perfectly paced teaching and the clever, engaging writing style as you dig into this awesome exploration of reinforcement learning fundamentals, effective deep learning techniques, and practical applications in this emerging field.
Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.
About the technology
We learn by interacting with our environment, and the rewards or punishments we experience guide our future behavior. Deep reinforcement learning brings that same natural process to artificial intelligence, analyzing results to uncover the most efficient ways forward. DRL agents can improve marketing campaigns, predict stock performance, and beat grand masters in Go and chess.
About the book
Grokking Deep Reinforcement Learning uses engaging exercises to teach you how to build deep learning systems. This book combines annotated Python code with intuitive explanations to explore DRL techniques. You’ll see how algorithms function and learn to develop your own DRL agents using evaluative feedback.
What's inside
ÌýÌýÌý An introduction to reinforcement learning
ÌýÌýÌý DRL agents with human-like behaviors
ÌýÌýÌý Applying DRL to complex situations
About the reader
For developers with basic deep learning experience.
About the author
Miguel Morales works on reinforcement learning at Lockheed Martin and is an instructor for the Georgia Institute of Technology’s Reinforcement Learning and Decision Making course.
Table of Contents
1 Introduction to deep reinforcement learning
2 Mathematical foundations of reinforcement learning
3 Balancing immediate and long-term goals
4 Balancing the gathering and use of information
5 Evaluating agents� behaviors
6 Improving agents� behaviors
7 Achieving goals more effectively and efficiently
8 Introduction to value-based deep reinforcement learning
9 More stable value-based methods
10 Sample-efficient value-based methods
11 Policy-gradient and actor-critic methods
12 Advanced actor-critic methods
13 Toward artificial general intelligence
450 pages, Paperback
Published April 1, 2020
39 people are currently reading
289 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 9 of 9 reviews
March 22, 2021
The topics are organized well, with each algorithm and each concept building off the previous ones. However, the book could use another editor to pare down the author's verbosity. His style is endearing, sure, but it reads like a first draft.
It isn't clear the level of familiarity the reader is expected to have. Some sections handhold from the fundamentals (such as policy/value iteration), while others assume intermediate to advanced level knowledge (ANNS, gradients, distributions). Overall, this is not a beginner's book, not for deep learning and not for RL either. That said, many RL materials currently highlight specific algorithms or concepts without a clear progression - this book does precisely that, and does it well.
It isn't clear the level of familiarity the reader is expected to have. Some sections handhold from the fundamentals (such as policy/value iteration), while others assume intermediate to advanced level knowledge (ANNS, gradients, distributions). Overall, this is not a beginner's book, not for deep learning and not for RL either. That said, many RL materials currently highlight specific algorithms or concepts without a clear progression - this book does precisely that, and does it well.
June 21, 2024
An amazing book about deep reinforcement learning. You need to have read a bit of deep learning to understand this book (at least the second half of the book). The first part which deals about tabular reinforcement learning, has the best explanation of the subject that I have found! He repeats again and again the important things, which is great to help you understand the subject.
The book deserves even a better score than 5 stars! However, as everything, it could have improved on two issues. The first one is that the author has a docker image to help you follow along without you having to install anything else, this after many hours of try, I never managed to make it work. Secondly, at the very end, some algorithms (especially on actor-critic and policy-gradient algorithms) the explanation was good, but much worse than the standards that the author had in the rest of the book.
The book deserves even a better score than 5 stars! However, as everything, it could have improved on two issues. The first one is that the author has a docker image to help you follow along without you having to install anything else, this after many hours of try, I never managed to make it work. Secondly, at the very end, some algorithms (especially on actor-critic and policy-gradient algorithms) the explanation was good, but much worse than the standards that the author had in the rest of the book.
July 30, 2023
good overview ( kindle version)
It is a good overview of deep reinforcement learning. The code and equations on the kindle version are difficult to read. I would suggest this to someone very new to the field, especially with limited coding experience. The one area I wish it had hit on better is the development of new environments, this is especially difficult area in research for high dimensional problems.
It is a good overview of deep reinforcement learning. The code and equations on the kindle version are difficult to read. I would suggest this to someone very new to the field, especially with limited coding experience. The one area I wish it had hit on better is the development of new environments, this is especially difficult area in research for high dimensional problems.
February 21, 2025
I really enjoy this book. The book worked as a great intro to RL and DRL topics. I read this book as a companion to a RL class. I felt this book simpler to understand than B&S due to the examples and code explaination.
May 6, 2025
Enlightenment - 10x @mimoralea !
Prior Journey:
- David Silver's DeepMind course: learned the mathematical framing
- Max Lapan's DRL hands on book: learned to code the algos
- Sutton & Barto's book: got lost in details
Prior Journey:
- David Silver's DeepMind course: learned the mathematical framing
- Max Lapan's DRL hands on book: learned to code the algos
- Sutton & Barto's book: got lost in details
July 24, 2021
Love the presentation style. Great for beginners. Think this book as precursor to Richard Sutton
December 18, 2021
Amazing, all you need to get started with RL.
January 6, 2020
brilliant
the book is still in MEAP and not completed yet, but perfectly compliments Stutton. Please go through the notebooks and graphs and discussions in Manning (in case you are going for the live book).
the book is still in MEAP and not completed yet, but perfectly compliments Stutton. Please go through the notebooks and graphs and discussions in Manning (in case you are going for the live book).
January 2, 2023
Excellent book - I enjoyed reading the book as well as the way the author explained all these complex concepts and methods. As a reference to the last chapter, the action of writing the book should receive a reward of +10. :)
Displaying 1 - 9 of 9 reviews
Can't find what you're looking for?
Get help and learn more about the design.