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
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
The Reinforcement Learning Workshop

You're reading from   The Reinforcement Learning Workshop Learn how to apply cutting-edge reinforcement learning algorithms to a wide range of control problems

Arrow left icon
Product type Paperback
Published in Aug 2020
Publisher Packt
ISBN-13 9781800200456
Length 822 pages
Edition 1st Edition
Languages
Arrow right icon
Authors (9):
Arrow left icon
Dr. Alexandra Galina Petre Dr. Alexandra Galina Petre
Author Profile Icon Dr. Alexandra Galina Petre
Dr. Alexandra Galina Petre
Anand N.S. Anand N.S.
Author Profile Icon Anand N.S.
Anand N.S.
Quan Nguyen Quan Nguyen
Author Profile Icon Quan Nguyen
Quan Nguyen
Anthony So Anthony So
Author Profile Icon Anthony So
Anthony So
Mayur Kulkarni Mayur Kulkarni
Author Profile Icon Mayur Kulkarni
Mayur Kulkarni
Aritra Sen Aritra Sen
Author Profile Icon Aritra Sen
Aritra Sen
Alessandro Palmas Alessandro Palmas
Author Profile Icon Alessandro Palmas
Alessandro Palmas
Emanuele Ghelfi Emanuele Ghelfi
Author Profile Icon Emanuele Ghelfi
Emanuele Ghelfi
Saikat Basak Saikat Basak
Author Profile Icon Saikat Basak
Saikat Basak
+5 more Show less
Arrow right icon
View More author details
Toc

Table of Contents (14) Chapters Close

Preface
1. Introduction to Reinforcement Learning 2. Markov Decision Processes and Bellman Equations FREE CHAPTER 3. Deep Learning in Practice with TensorFlow 2 4. Getting Started with OpenAI and TensorFlow for Reinforcement Learning 5. Dynamic Programming 6. Monte Carlo Methods 7. Temporal Difference Learning 8. The Multi-Armed Bandit Problem 9. What Is Deep Q-Learning? 10. Playing an Atari Game with Deep Recurrent Q-Networks 11. Policy-Based Methods for Reinforcement Learning 12. Evolutionary Strategies for RL Appendix

Summary

In this chapter, the MAB problem and its motivation as a reinforcement learning and artificial intelligence problem were introduced. We explored a plethora of algorithms that are commonly used to solve the MAB problem, including the Greedy algorithm and its variants, UCB, and Thompson Sampling. Via these algorithms, we were exposed to unique insights and heuristics on how to balance exploration and exploitation (which is one of the most fundamental components of reinforcement learning) such as random exploration, optimism under uncertainty, or sampling from Bayesian posterior distributions.

This knowledge was put into practice as we learned how to implement these algorithms from scratch in Python. During this process, we also examined the importance of analyzing MAB algorithms over many repeated experiments to obtain robust results. This procedure is integral for any analysis framework that involves randomness. Finally, in this chapter's activity, we applied our knowledge...

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