Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Deep Reinforcement Learning with Python

You're reading from   Deep Reinforcement Learning with Python Master classic RL, deep RL, distributional RL, inverse RL, and more with OpenAI Gym and TensorFlow

Arrow left icon
Product type Paperback
Published in Sep 2020
Publisher Packt
ISBN-13 9781839210686
Length 760 pages
Edition 2nd Edition
Languages
Arrow right icon
Author (1):
Arrow left icon
Sudharsan Ravichandiran Sudharsan Ravichandiran
Author Profile Icon Sudharsan Ravichandiran
Sudharsan Ravichandiran
Arrow right icon
View More author details
Toc

Table of Contents (22) Chapters Close

Preface 1. Fundamentals of Reinforcement Learning 2. A Guide to the Gym Toolkit FREE CHAPTER 3. The Bellman Equation and Dynamic Programming 4. Monte Carlo Methods 5. Understanding Temporal Difference Learning 6. Case Study – The MAB Problem 7. Deep Learning Foundations 8. A Primer on TensorFlow 9. Deep Q Network and Its Variants 10. Policy Gradient Method 11. Actor-Critic Methods – A2C and A3C 12. Learning DDPG, TD3, and SAC 13. TRPO, PPO, and ACKTR Methods 14. Distributional Reinforcement Learning 15. Imitation Learning and Inverse RL 16. Deep Reinforcement Learning with Stable Baselines 17. Reinforcement Learning Frontiers 18. Other Books You May Enjoy
19. Index
Appendix 1 – Reinforcement Learning Algorithms 1. Appendix 2 – Assessments

Soft actor-critic

Now, we will look into another interesting actor-critic algorithm, called SAC. This is an off-policy algorithm and it borrows several features from the TD3 algorithm. But unlike TD3, it uses a stochastic policy . SAC is based on the concept of entropy. So first, let's understand what is meant by entropy. Entropy is a measure of the randomness of a variable. It basically tells us the uncertainty or unpredictability of the random variable and is denoted by .

If the random variable always gives the same value every time, then we can say that its entropy is low because there is no randomness. But if the random variable gives different values, then we can say that its entropy is high.

For an example, consider a dice throw experiment. Every time a dice is thrown, if we get a different number, then we can say that the entropy is high because we are getting a different number every time and there is high uncertainty since we don't know which number will...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $19.99/month. Cancel anytime
Banner background image