https://github.com/llSourcell/Game-AI

Game AI for Machine Learning for Hackers #3
https://github.com/llSourcell/Game-AI

Last synced: 16 days ago
JSON representation

Game AI for Machine Learning for Hackers #3

• Host: GitHub
• URL: https://github.com/llSourcell/Game-AI
• Owner: llSourcell
• Created: 2016-05-15T07:28:00.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2017-03-03T19:41:16.000Z (over 7 years ago)
• Last Synced: 2024-08-01T08:10:10.374Z (3 months ago)
• Language: Python
• Size: 15.6 KB
• Stars: 156
• Watchers: 20
• Forks: 82
• Open Issues: 7
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
Overview

====

A Tensorflow DQN implementation based on [DeepMind's DQN](https://storage.googleapis.com/deepmind-data/assets/papers/DeepMindNature14236Paper.pdf) for playing Atari games.This the code for 'Build a game AI' on [Youtube](https://youtu.be/HBAUeJkFMH0)

## Dependencies

- [gym](https://gym.openai.com)

- [Tensorflow](https://www.tensorflow.org)

- [virtualenv] (https://virtualenv.pypa.io/en/latest/installation.html)

## Basic Usage

To run, type the following into terminal

`python atari.py --game `

It will run `SpaceInvaders-v0` by default but you can use other game names as well. Add `--display true` to the above command line argument if you'd like to see the game while it trains

## Credits

Credit for the vast majority of code here goes to [Kee Hyun Won](https://github.com/kihyunwon). I've merely created a wrapper to get people started.