achukka / ping_pong_agent Goto Github PK

This repository contains code for simulating ping pong game using pygame. In this setup, we have an Evil Agent and an RL agent who learns the actions with help of Deep Q Network. The agent gets better by maximising its score through trial and error. The DQN is a Convolutional Neural Network that reads raw pixel data from the pygame and game score. With these parameters it learns the actions(moves) that maximizes its score.

This code is written in python. To use it you will need:

• Python 2.7
• [Tensorflow] (https://www.tensorflow.org)
• [OpenCV] (http://docs.opencv.org/2.4/doc/tutorials/introduction/linux_install/linux_install.html)
• Pygame
• NumPy

You can run the agent by the following command:

python rl_algo.py

This code was by malreddysid I've merely wrapped and updated it.