##Overview This is the code for the Live Youtube session by @Sirajology. In this live session I build the game of Pong from scratch. Then I build a Deep Q Network that gets better and better over time through trial and error. The DQN is a convolutional neural network that reads in pixel data from the game and the game score. Using just those 2 parameters, it learns what moves it needs to make to become better.
##Installation
- tensorflow (https://www.tensorflow.org)
- cv2 (http://www.pyimagesearch.com/2015/06/15/install-opencv-3-0-and-python-2-7-on-osx/)
- numpy
- random
- collections
- pygame
use pip to install the dependencies. Tensorflow and cv2 are more manual. Links provided above ^
##Usage
Run it like this in terminal. The longer you let it run, the better it will get.
python RL.py
##Credits
This code was by malreddysid i've merely wrapped, updated, and documented it.