Amazon calculates a product’s star ratings based on a machine learned model instead of a raw data average. The model takes into account factors including the age of a rating, whether the ratings are from verified purchasers, and factors that establish reviewer trustworthiness.
Arrived in just one day (Thank you Amazon). The book is very well written. The key concepts are clearly explained and easy to understand. I definitely recommend this book to anyone that wants to grab the key ideas and start working on Deep RL right away. I also recommend the book from Sutton and Barto as a supplement to this book if you want to dive deeper into theoretical RL.
Wow, what a book! This is exactly what I was looking for: a hands-on introduction to Deep RL that covers all of the prevailing contemporary theory and applications. To boot, the authors' associated SLM Lab GitHub repo (covered extensively throughout the book) makes it easy to construct, deploy, and optimize state-of-the-art agents across a broad range of environments. Thank you, Laura and Keng :)
Reviewed in the United States on February 22, 2020
The authors have taken great pains to keep the book relevant to the times. The fact that a companion git repo is available to try out what you’re reading about in each chapter shows the Theory and Practice approach they describe. This is exactly the right way to learn a complex new science
The theory in the chapters are easy to digest, quick links, code and snippets available to try out on SLM lab, and a great reference to get back to when putting Deep RL to work in your real world applications. Highly recommend to anyone who’s beginning to explore RL and wants to start using it to build robot arms, game agents, or achieve AGI