Building a Pong playing AI
This repository contains the resources needed for the tutorial, Building a Pong playing AI in just 1 hour(Plus 4 days training time). The full video for the tutorial is on youtube here.
Installation Guide for OS X
Tested on a Macbook Pro (late 2013) with El Capitan, unsure if GPU-support works.
Install some image libraries and a X framework for MacOS:
brew install sdl_image brew install Caskroom/cask/xquartz
Clone the repo:
git clone email@example.com:DanielSlater/PyDataLondon2016.git cd PyDataLondon2016/
Create a virtual environment for Python 2:
conda create --name pong-ai-27 python=2 source activate pong-ai-27
Install listed dependencies plus
conda install matplotlib numpy opencv
conda install -c https://conda.anaconda.org/jjhelmus tensorflow conda install -c https://conda.binstar.org/quasiben pygame
git submodule init git submodule update
common in folder
cd examples/ ln -s ../resources/ ln -s ../common/
Run an example:
Linux Nvidea GPU installation Guide
Tensorflow requires an NVidia GPU and only runs on Linux/Mac so if you don't have these Theano is an option (see below). The examples are all in Tensorflow, but that translates very easily to Theano and we have an example Q-learning Theano implementation that can be extended to work with Pong.
Windows/non nvidia gpu
Either 2 or 3 is fine.
Download which ever version matches the version of Python you plan on using.
Download anaconda and install packages:
conda install mingw libpython numpy
Clone Theano repo:
git clone https://github.com/Theano/Theano.git
Install theano package:
cd Theano python setup.py develop
###Docker environment alternative
Have a look at the Makefile, essentially this helps you setup an xquartz environment exposed to a docker container along with the required dependencies. 'make all' should in theory launch you into an environment capable of running th examples straight away.
Used for running reinforcement learning agents against PyGame
PyGame implementation of pong
Even pong can be hard if you're just a machine. Half pong is a simplified version of pong, if you can believe it. The score and other bits of noise are removed from the game. There is only 1 bar and it is only 80x80 pixels which speeds up training and removes the need to downsize the screen