You're reading from Deep Reinforcement Learning Hands-On Apply modern RL methods to practical problems of chatbots, robotics, discrete optimization, web automation, and more

Product type Paperback

Published in Jan 2020

Publisher Packt

ISBN-13 9781838826994

Length 826 pages

Edition 2nd Edition

Languages

Python

Tools

Deep Reinforcement Learning

Concepts

Chatbots

Author (1):

Maxim Lapan

View More author details

Table of Contents (28) Chapters

Preface

1. What Is Reinforcement Learning?

2. OpenAI Gym FREE CHAPTER

3. Deep Learning with PyTorch

4. The Cross-Entropy Method

5. Tabular Learning and the Bellman Equation

6. Deep Q-Networks

7. Higher-Level RL Libraries

8. DQN Extensions

9. Ways to Speed up RL

10. Stocks Trading Using RL

11. Policy Gradients – an Alternative

12. The Actor-Critic Method

13. Asynchronous Advantage Actor-Critic

14. Training Chatbots with RL

15. The TextWorld Environment

16. Web Navigation

17. Continuous Action Space

18. RL in Robotics

19. Trust Regions – PPO, TRPO, ACKTR, and SAC

20. Black-Box Optimization in RL

21. Advanced Exploration

22. Beyond Model-Free – Imagination

23. AlphaGo Zero

24. RL in Discrete Optimization

25. Multi-agent RL

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...