Code for "Spinning Up a Pong AI With Deep RL" on FloydHub
Switch branches/tags
Nothing to show
Clone or download
Latest commit 33df435 Dec 7, 2018

Spinning Up a Pong AI With Deep Reinforcement Learning

the hard-coded AI that only follows the ball (left) vs. our trained AI

Run on FloydHub

Note: These are the Jupyter Notebooks for my article Spinning Up a Pong AI With Deep Reinforcement Learning on FloydHub.

Within a few years, Deep Reinforcement Learning will completely transform robotics, an industry with the potential to automate 64 percent of manufacturing. Hard-to-engineer behaviors will become a piece of cake, so long as there are enough Deep RL practitioners to implement them.

The following notebooks (file ending with .ipynb) detail how to train a model in Keras that plays the game of Pong using simple Policy Gradient techniques:

Files overview

#Main notebooks
  |train.ipynb                             #Main notebook to train the Pong agent in Keras
  |train-with-log.ipynb                    #Same as above but with tensorflow logs and model saving/loading

#Demo notebooks
  |demo.ipynb                              #Simple notebook to generate a gif with a random model
  |demo_black_and_white.ipynb              #Same as above but generate the gif for the pre-processed frame diff

  |                              #To support the gif generation
  |                          #Tool to easily plot variable
  |                             #Functions used in karpathy's original RL Pong post

#FloydHub specific  
  |floyd.yml                               #Tells what to execute when launching a job
  |floyd_requirements.txt                  #Necessary packages to install
#Trained weights
  |my_model_weights.h5                     #Saved weights after training

Demo of random agent

Gif generated with demo.ipynb:

random agent

Gif generated with demo_black_and_white.ipynb:

random agent

Pre-processed frames in black and white

Run the code on FloydHub

Run on FloydHub

Click the above blue button to open a Workspace on FloydHub where you will find the same environment.


pip install keras gym jupyter
git clone
cd spinning-up-a-Pong-AI-with-deep-RL
jupyter notebook

Go do the desired notebook, files that end with '.ipynb'. To run the model, go to the menu then click on Cell > Run all