What’s new in this second edition of Deep Reinforcement Learning Hands-On? This edition is devoted to the very latest reinforcement learning tools and techniques, focusing on new innovations in this emerging field. It includes six new chapters that give readers the hands-on ability to code intelligent learning agents to perform a range of practical tasks. Topics include using the TextWorld environment from Microsoft Research to solve text-based interactive fiction games, solving discrete optimization problems (showcased using the Rubik’s Cube), and learning to apply RL methods to the robotics domain. The book then dives into an important aspect of RL methods: advanced exploration. Several modern exploration techniques are described, implemented, and compared. Readers will also discover basic methods applied to a multi-agent environment. Finally, all examples have been updated for PyTorch 1.3. PyTorch Ignite has also been introduced to make the coding more concise. What are the key takeaways you want readers to get from this book? I want readers to feel that modern RL is a fun, practical, and useful field. Information about recent research is widely available, but it is too specialized and abstract for most people to easily understand. Getting to grips with the practical aspects of RL application is even more difficult. The goal is to help readers understand RL methods using real-life, relatable problems, rather than from reading math-heavy research papers, which are useful when you already have the intuition behind the field. If readers are new to this field, these papers might not be the best source of information, at least not at first. This book addresses the obvious lack of practical and structured information about RL methods and approaches. What factors are driving the development of RL in AI, and how does this book explore this field? RL development is being driven by several companies and research groups, including Google, Microsoft, and Facebook. It requires lots of investment in research, as there are not that many directions that are developed enough to be able to just take their methods and apply them to a problem. This is similar to how natural language processing and computer vision were several years ago. Having said that, the field of RL is attracting lots of attention, both from researchers and practitioners. This book helps readers to understand RL methods using real-life problems, and make the exciting RL domain accessible to a much wider audience than just research groups or large AI companies.
✔ Author(s): Maxim Lapan
✔ Title: Deep Reinforcement Learning Hands-On: Apply modern RL methods to practical problems of chatbots, robotics, discrete optimization, web automation, and more, 2nd Edition
✔ Rating : 4.5 out of 5 base on (160 reviews)
✔ ISBN-10: 1838826998
✔ ISBN-13: 9781838826994
✔ Language: English
✔ Format ebook: PDF, EPUB, Kindle, Audio, HTML and MOBI
✔ Device compatibles: Android, iOS, PC and Amazon Kindle
Readers' opinions about Deep Reinforcement Learning Hands by Maxim Lapan
Elaine Leonard
I must confess, this book made me shed tears like never before. The themes of love, loss, and resilience struck a chord with my soul. It was an emotional journey I'm grateful to have taken.
Sarah Franklin
The plot was incredibly well-crafted, with twists and turns that kept me hooked until the very last page. It was impossible to predict what would happen next.
Sydney Richardson
I'm already planning to reread this book. It's one of those stories that you can revisit again and again, discovering new layers of meaning each time.
