Description
PyData London 2016
We will build an AI that can master the game of Pong in just 1 hour. In the course of this we will talk through some of the tools involved. Q-learning , Deep learning and Convolutional nets and how they fit into Pong. Most of the heavy lifting will be done using Google's recently released Tensorflow libraries.
We will start by setting up a Python an agent in Pong that moves completely randomly. I will then talk over what Q-learning is and how it works and a bit about Convolutional nets. We will then build the actual agent using Tensorflow.
Full code will be given, including links for downloading the resources required, so hopefully the audience can build this on their laptops. I would hope to give enough information that users will be able to make there own agents independently once finished.
Slides available here: https://speakerdeck.com/danielslater/building-a-pong-ai