Summary

Humans learn best from feedback—we are encouraged to take actions that lead to positive results while deterred by decisions with negative consequences. This reinforcement process can be applied to computer programs allowing them to solve more complex problems that classical programming cannot. Deep Reinforcement Learning in Action teaches you the fundamental concepts and terminology of deep reinforcement learning, along with the practical skills and techniques you’ll need to implement it into your own projects.

Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.

About the technology

Deep reinforcement learning AI systems rapidly adapt to new environments, a vast improvement over standard neural networks. A DRL agent learns like people do, taking in raw data such as sensor input and refining its responses and predictions through trial and error.

About the book

Deep Reinforcement Learning in Action teaches you how to program AI agents that adapt and improve based on direct feedback from their environment. In this example-rich tutorial, you’ll master foundational and advanced DRL techniques by taking on interesting challenges like navigating a maze and playing video games. Along the way, you’ll work with core algorithms, including deep Q-networks and policy gradients, along with industry-standard tools like PyTorch and OpenAI Gym.

What's inside

    Building and training DRL networks
    The most popular DRL algorithms for learning and problem solving
    Evolutionary algorithms for curiosity and multi-agent learning
    All examples available as Jupyter Notebooks

About the reader

For readers with intermediate skills in Python and deep learning.

About the author

Alexander Zai is a machine learning engineer at Amazon AI. Brandon Brown is a machine learning and data analysis blogger.

Table of Contents

PART 1 - FOUNDATIONS

1. What is reinforcement learning?

2. Modeling reinforcement learning problems: Markov decision processes

3. Predicting the best states and actions: Deep Q-networks

4. Learning to pick the best policy: Policy gradient methods

5. Tackling more complex problems with actor-critic methods

PART 2 - ABOVE AND BEYOND

6. Alternative optimization methods: Evolutionary algorithms

7. Distributional DQN: Getting the full story

8.Curiosity-driven exploration

9. Multi-agent reinforcement learning

10. Interpretable reinforcement learning: Attention and relational models

11. In conclusion: A review and roadmap

About the Author

Alexander Zai is a Machine Learning Engineer at Amazon AI working on MXNet that powers a suite of AWS machine learning products.

Brandon Brown is a Machine Learning and Data Analysis blogger at outlace.com committed to providing clear teaching on difficult topics for newcomers.

"About this title" may belong to another edition of this title.

Store Description

**Please note our transit times are from the date of dispatch.** We first started out as ?The Paperback Exchange,? a chain of physical bookstores where we would part exchange your beloved books for new stories to transport you to faraway places. However, as shopping started to evolve to online shops and marketplaces, we bid our stores goodbye to become ?PBShop.? This transition has only allowed us to blossom as we now ship thousands of titles to book lovers across the globe. We pride ourselves in being a community of local book lovers which allows our passion and devotion to shine in everything we do. In 2020 we not only celebrated our 20th birthday but our 1st birthday as being completely employee owned after becoming an E.O.T in September 2019. We are proud to be different and embrace standing apart on a book mountain by working from a virtual inventory which allows us to provide thousands of books that may be difficult to get for your bookshelf or your studies. Working with a number of different suppliers allows us to explore other avenues such as puzzles, sheet music and even stationery so we really do have something for everyone. Life is about being versatile in all realms of existence. If this is your first purchase with us, or you are a returning customer, we would like to welcome you to the PBShop family, for there is no friend as loyal as a book. We are a company who put our customers at the centre of everything we do as we understand the importance of reading because once you learn to read, you will forever be free. There are a whole lot of things in this world of ours that we are yet to explore, which is why we will forever inspire curious minds.

Visit Seller's Storefront

Seller's business information

Pbshop.co.uk
Unit 22 Horcott Industrial Estate, Horcott Road, Fairford, GL7 4BX, United Kingdom

Sale & Shipping Terms

Terms of Sale

Returns Policy
We ask all customers to contact us for authorisation should they wish to return their order. Orders returned without authorisation may not be credited.
If you wish to return, please contact us within 14 days of receiving your order to obtain authorisation.
Returns requested beyond this time will not be authorised.
Our team will provide full instructions on how to return your order and once received our returns department will process your refund.
Please note the cost to return any...

More Information

Shipping Terms

Orders are shipped from our UK warehouse. Delivery thereafter is between 4 and 14 business days. Please contact us if you have any queries about our services or products.

Shipping rates from United Kingdom to U.S.A.

Shipping rates from United Kingdom to U.S.A.
Order quantity	10 to 20 business days	10 to 20 business days
First item	US$ 7.75	US$ 7.78

Delivery times are set by sellers and vary by carrier and location. Orders passing through Customs may face delays and buyers are responsible for any associated duties or fees. Sellers may contact you regarding additional charges to cover any increased costs to ship your items.