Book Image

Deep Reinforcement Learning Hands-On - Second Edition

By : Maxim Lapan
Book Image

Deep Reinforcement Learning Hands-On - Second Edition

By: Maxim Lapan

Overview of this book

Deep Reinforcement Learning Hands-On, Second Edition is an updated and expanded version of the bestselling guide to the very latest reinforcement learning (RL) tools and techniques. It provides you with an introduction to the fundamentals of RL, along with the hands-on ability to code intelligent learning agents to perform a range of practical tasks. With six new chapters devoted to a variety of up-to-the-minute developments in RL, including discrete optimization (solving the Rubik's Cube), multi-agent methods, Microsoft's TextWorld environment, advanced exploration techniques, and more, you will come away from this book with a deep understanding of the latest innovations in this emerging field. In addition, you will gain actionable insights into such topic areas as deep Q-networks, policy gradient methods, continuous control problems, and highly scalable, non-gradient methods. You will also discover how to build a real hardware robot trained with RL for less than $100 and solve the Pong environment in just 30 minutes of training using step-by-step code optimization. In short, Deep Reinforcement Learning Hands-On, Second Edition, is your companion to navigating the exciting complexities of RL as it helps you attain experience and knowledge through real-world examples.
Table of Contents (28 chapters)
26
Other Books You May Enjoy
27
Index

The code outline

Okay, now let's switch to the code, which is in directory Chapter24 in the book's repository. In this section, I'm going to give a quick outline of my implementation and the key design decisions, but before that, I have to emphasize the important points about the code to set up the correct expectations:

  • I'm not a researcher, so the original goal of this code was just to reimplement the paper's method. Unfortunately, the paper has very few details about the exact hyperparameters used, so I had to guess and experiment a lot, and still, my results are very different from those published in the paper.
  • At the same time, I've tried to implement everything in a general way to simplify further experiments. For example, the exact details about the cube state and transformations are abstracted away, which allows us to implement more puzzles similar to the 3×3 cube just by adding a new module. In my code, two cubes are implemented...