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
Python Reinforcement Learning

You're reading from   Python Reinforcement Learning Solve complex real-world problems by mastering reinforcement learning algorithms using OpenAI Gym and TensorFlow

Arrow left icon
Product type Course
Published in Apr 2019
Publisher Packt
ISBN-13 9781838649777
Length 496 pages
Edition 1st Edition
Languages
Arrow right icon
Authors (4):
Arrow left icon
Yang Wenzhuo Yang Wenzhuo
Author Profile Icon Yang Wenzhuo
Yang Wenzhuo
Sean Saito Sean Saito
Author Profile Icon Sean Saito
Sean Saito
Sudharsan Ravichandiran Sudharsan Ravichandiran
Author Profile Icon Sudharsan Ravichandiran
Sudharsan Ravichandiran
Rajalingappaa Shanmugamani Rajalingappaa Shanmugamani
Author Profile Icon Rajalingappaa Shanmugamani
Rajalingappaa Shanmugamani
Arrow right icon
View More author details
Toc

Table of Contents (27) Chapters Close

Title Page
About Packt
Contributors
Preface
1. Introduction to Reinforcement Learning FREE CHAPTER 2. Getting Started with OpenAI and TensorFlow 3. The Markov Decision Process and Dynamic Programming 4. Gaming with Monte Carlo Methods 5. Temporal Difference Learning 6. Multi-Armed Bandit Problem 7. Playing Atari Games 8. Atari Games with Deep Q Network 9. Playing Doom with a Deep Recurrent Q Network 10. The Asynchronous Advantage Actor Critic Network 11. Policy Gradients and Optimization 12. Balancing CartPole 13. Simulating Control Tasks 14. Building Virtual Worlds in Minecraft 15. Learning to Play Go 16. Creating a Chatbot 17. Generating a Deep Learning Image Classifier 18. Predicting Future Stock Prices 19. Capstone Project - Car Racing Using DQN 20. Looking Ahead 1. Assessments 2. Other Books You May Enjoy Index

What is RL?


Consider that you are teaching the dog to catch a ball, but you cannot teach the dog explicitly to catch a ball; instead, you will just throw a ball, and every time the dog catches the ball, you will give it a cookie. If it fails to catch the ball, you will not give a cookie. The dog will figure out what actions made it receive a cookie and will repeat those actions.

Similarly, in a RL environment, you will not teach the agent what to do or how to do instead, you will give a reward to the agent for each action it does. The reward may be positive or negative. Then the agent will start performing actions which made it receive a positive reward. Thus, it is a trial and error process. In the previous analogy, the dog represents the agent. Giving a cookie to the dog upon catching the ball is a positive reward, and not giving a cookie is a negative reward.

There might be delayed rewards. You may not get a reward at each step. A reward may be given only after the completion of a task. In some cases, you get a reward at each step to find out that whether you are making any mistakes. 

Imagine you want to teach a robot to walk without getting stuck by hitting a mountain, but you will not explicitly teach the robot not to go in the direction of the mountain:

Instead, if the robot hits and get stuck on the mountain, you will take away ten points so that robot will understand that hitting the mountain will result in a negative reward and it will not go in that direction again:

You will give 20 points to the robot when it walks in the right direction without getting stuck. So the robot will understand which is the right path and will try to maximize the rewards by going in the right direction:

The RL agent can explore different actions which might provide a good reward or it can exploit (use) the previous action which resulted in a good reward. If the RL agent explores different actions, there is a great possibility that the agent will receive a poor reward as all actions are not going to be the best one. If the RL agent exploits only the known best action, there is also a great possibility of missing out on the best action, which might provide a better reward. There is always a trade-off between exploration and exploitation. We cannot perform both exploration and exploitation at the same time. We will discuss the exploration-exploitation dilemma in detail in the upcoming chapters.

You have been reading a chapter from
Python Reinforcement Learning
Published in: Apr 2019
Publisher: Packt
ISBN-13: 9781838649777
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