Reader small image

You're reading from  Reinforcement Learning Algorithms with Python

Product typeBook
Published inOct 2019
Reading LevelBeginner
PublisherPackt
ISBN-139781789131116
Edition1st Edition
Languages
Right arrow
Author (1)
Andrea Lonza
Andrea Lonza
author image
Andrea Lonza

Andrea Lonza is a deep learning engineer with a great passion for artificial intelligence and a desire to create machines that act intelligently. He has acquired expert knowledge in reinforcement learning, natural language processing, and computer vision through academic and industrial machine learning projects. He has also participated in several Kaggle competitions, achieving high results. He is always looking for compelling challenges and loves to prove himself.
Read more about Andrea Lonza

Right arrow

Playing Flappy Bird

Later in this chapter, we'll develop and test an IL algorithm called DAgger on a new environment. The environment named Flappy Bird emulates the famous Flappy Bird game. Here, our mission is to give you the tools needed to implement code using this environment, starting from the explanation of the interface.

Flappy Bird belongs to the PyGame Learning Environment (PLE), a set of environments that mimic the Arcade Learning Environment (ALE) interface. This is similar to the Gym interface, and later we'll see the differences, although it's simple to use.

The goal of Flappy Bird is to make the bird fly through vertical pipes without hitting them. It is controlled by only one action that makes it flap its wings. If it doesn't fly, it progresses in a decreasing trajectory determined by gravity. A screenshot of the environment is shown here:

...
lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
Reinforcement Learning Algorithms with Python
Published in: Oct 2019Publisher: PacktISBN-13: 9781789131116

Author (1)

author image
Andrea Lonza

Andrea Lonza is a deep learning engineer with a great passion for artificial intelligence and a desire to create machines that act intelligently. He has acquired expert knowledge in reinforcement learning, natural language processing, and computer vision through academic and industrial machine learning projects. He has also participated in several Kaggle competitions, achieving high results. He is always looking for compelling challenges and loves to prove himself.
Read more about Andrea Lonza