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 Rubik's Cube and combinatorial optimization

I doubt it's possible to find a person who hasn't heard about the Rubik's Cube, so I'm not going to repeat the Wikipedia description (https://en.wikipedia.org/wiki/Rubik%27s_Cube) of this puzzle, but rather focus on the connections it has to mathematics and computer science. If it's not explicitly stated, by "cube" I mean the 3×3 classic Rubik's Cube. There are lots of variations based on the original 3×3 puzzle, but they are still far less popular than the classic invention.

Despite being quite simple in terms of mechanics and the task at hand, the cube is quite a tricky object in terms of all the transformations we can make by possible rotations of its sides. It was calculated that in total, the cube has ~4.33 × 10¹⁹ distinct states reachable by rotating it. That's only the states that are reachable without disassembling the cube; by taking it apart and then assembling...