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
Keras Reinforcement Learning Projects

You're reading from   Keras Reinforcement Learning Projects 9 projects exploring popular reinforcement learning techniques to build self-learning agents

Arrow left icon
Product type Paperback
Published in Sep 2018
Publisher Packt
ISBN-13 9781789342093
Length 288 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Author (1):
Arrow left icon
Giuseppe Ciaburro Giuseppe Ciaburro
Author Profile Icon Giuseppe Ciaburro
Giuseppe Ciaburro
Arrow right icon
View More author details
Toc

Table of Contents (13) Chapters Close

Preface 1. Overview of Keras Reinforcement Learning FREE CHAPTER 2. Simulating Random Walks 3. Optimal Portfolio Selection 4. Forecasting Stock Market Prices 5. Delivery Vehicle Routing Application 6. Continuous Balancing of a Rotating Mechanical System 7. Dynamic Modeling of a Segway as an Inverted Pendulum System 8. Robot Control System Using Deep Reinforcement Learning 9. Handwritten Digit Recognizer 10. Playing the Board Game Go 11. What's Next? 12. Other Books You May Enjoy

The FrozenLake environment

The FrozenLake environment is a 4 × 4 grid that contains four possible areas: Safe (S), Frozen (F), Hole (H), and Goal (G). The agent controls the movement of a character in a grid world, and moves around the grid until it reaches the goal or the hole. Some tiles of the grid are walkable, and others lead to the agent falling into the water. If it falls into the hole, it has to start from the beginning and is rewarded the value 0. Additionally, the movement direction of the agent is uncertain and only partially depends on the chosen direction. The agent is rewarded for finding a walkable path to a goal tile. The agent has four possible moves: up, down, left, and right. The process continues until it learns from every mistake and reaches the goal eventually.

The surface is described using a grid like the following:

  • SFFF (S: starting point, safe)
  • ...
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