# Grokking Deep Reinforcement Learning

Source: https://listme.name/books/grokking-deep-reinforcement-learning
Website: https://www.manning.com/books/grokking-deep-reinforcement-learning

Practical introduction to deep reinforcement learning with exercises

Grokking Deep Reinforcement Learning is a book by Miguel Morales, published by Manning in 2020. It teaches deep reinforcement learning through clear examples and exercises, aiming at intelligent systems that learn from experience. The Manning page offers an excerpt, and the 2020 print edition runs to 472 pages.

The book introduces deep reinforcement learning, which combines reinforcement learning with deep neural networks, and it builds the ideas step by step through worked examples. The Manning description emphasizes clear examples and exercises, and presents the goal as building intelligent systems that learn from experience. The approach is practical, so it suits readers who want to implement agents.

It is paid and has no free full text, but the Manning page offers an excerpt before purchase. Compared with Sutton and Barto, it is more hands-on and less rigorous, and it sits below the textbooks for mathematical depth. It is a useful companion to those textbooks for readers who want to write agents as well as read the theory.

- Paid | Print
- Price: Print edition from Manning; excerpt on the publisher site
- Checked: 2026-10-10

## Strengths

- Worked examples and exercises
- Practical focus on building agents
- Recent 2020 edition

## Limits

- Less mathematical depth than the theory texts
- No free full text online

## Rankings

- #10 of 10 in [best Reinforcement learning and edge ML books](https://listme.name/best/reinforcement-learning-and-edge-ml-books), score 83.0: A practical, exercise-driven introduction to deep reinforcement learning from Manning. It has less mathematical depth than the textbooks above it and no free full text, so it suits builders more than theorists.

## Alternatives

- [Reinforcement Learning: An Introduction](https://listme.name/books/reinforcement-learning-an-introduction), score 94.0
- [Reinforcement Learning and Optimal Control](https://listme.name/books/reinforcement-learning-and-optimal-control), score 90.5
- [TinyML](https://listme.name/books/tinyml-book), score 89.0
- [Bandit Algorithms](https://listme.name/books/bandit-algorithms), score 88.0
- [Efficient Processing of Deep Neural Networks](https://listme.name/books/efficient-processing-of-deep-neural-networks), score 87.5
- [Reinforcement Learning: Theory and Algorithms](https://listme.name/books/reinforcement-learning-theory-and-algorithms), score 86.0
- [Foundations of Deep Reinforcement Learning](https://listme.name/books/foundations-of-deep-reinforcement-learning), score 85.0
- [Algorithms for Reinforcement Learning](https://listme.name/books/algorithms-for-reinforcement-learning), score 84.5