This repository contains an implementation of a Deep Q-learning algorithm (DQN) used to solve MsPacman game using the Gym environment.
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
In order to run the notebook you need to install tensorflow and gym (included the atari games).
$ pip install tensorflow
$ pip install 'gym[all]'
Next, install git if you don't have already it and run the following commands on your terminal
$ cd $HOME # or any other development directory you prefer
$ git clone https://github.com/andri27-ts/PacManRL.git
$ cd PacManRL
To visualize the loss function and the histograms of the NN layers using Tensorboard, run on your terminal
$ cd $HOME # or any other development directory you prefer
$ cd PacManRL
$ tensorboard --logdir tf_logs/