Fun: Playing Flappy Bird

In this example, we will see a Deep Learning agent playing Flappy Bird! We have the option to train the agent ourself, but for now let us just start with the pre-trained network given by the author. Note that the following agent is able to play without being told any information about the structure of the game or its rules. It automatically discovers the rules of the game by finding out how it did on each iteration.

We will be following this repository by Yenchen Lin.

Steps

• git clone https://github.com/yenchenlin/DeepLearningFlappyBird.git
• cd DeepLearningFlappyBird
• python deep_q_network.py

If all went correctly, you should be seeing a Deep Learning based agent play Flappy Bird! The repository contains instructions for training your own agent if you’re interested!