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 experiment results

Unfortunately, the paper provided no details about very important aspects of the method, like training hyperparameters, how deeply cubes were scrambled during the training, and the obtained convergence. To fill in the missing blanks, I did lots of experiments with various values of hyperparameters, but still my results are very different from those published in the paper. First of all, the training convergence of the original method is very unstable. Even with a small learning rate and a large batch size, the training eventually diverges, with the value loss component growing exponentially. Examples of this behavior are shown on the figure that follows.

Figure 24.5: The policy loss (left) and value loss (right) of two runs of the paper's method

After several experiments with this, I came to the conclusion that this behavior is a result of the wrong value objective being proposed in the method. Indeed, in the formula , the value returned by the...