https://github.com/ravi72munde/chrome-dino-reinforcement-learning

An RL implementation in Keras
https://github.com/ravi72munde/chrome-dino-reinforcement-learning

chrome-dino-game convolutional-neural-networks q-learning reinforcement-learning

Last synced: 6 months ago
JSON representation

An RL implementation in Keras

• Host: GitHub
• URL: https://github.com/ravi72munde/chrome-dino-reinforcement-learning
• Owner: ravi72munde
• License: mit
• Created: 2018-02-13T03:56:40.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2018-07-04T17:26:32.000Z (almost 7 years ago)
• Last Synced: 2023-10-19T20:17:25.745Z (over 1 year ago)
• Topics: chrome-dino-game, convolutional-neural-networks, q-learning, reinforcement-learning
• Language: Jupyter Notebook
• Homepage: https://medium.com/acing-ai/how-i-build-an-ai-to-play-dino-run-e37f37bdf153
• Size: 138 MB
• Stars: 98
• Watchers: 8
• Forks: 19
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Chrome-Dino-Reinforcement-Learning

NOTE: This repo is the basic implementation with few limitations. Please refer the new repo at https://github.com/Paperspace/DinoRunTutorial

https://blog.paperspace.com/dino-run/

A Deep Convolutional Neural Network to play Google Chrome's offline Dino Run game by learning action patterns from visual input using a model-less Reinforcement Learning Algorithm

NOTE: This is a basic-implementation repository with some limitations. Please refer https://github.com/Paperspace/DinoRunTutorial where I've used a GPU VM for better results, with scores upto 4000

Refer the jupyter notebook for detailed implementation :


https://github.com/ravi72munde/Chrome-Dino-Reinforcement-Learning/blob/master/Reinforcement%20Learning%20Dino%20Run.ipynb

# Installation 

Start by cloning the repository







`$ git clone https://github.com/ravi72munde/Chrome-Dino-Reinforcement-Learning.git`




`Dependencies can be installed using pip install or conda install for Anaconda environment`



Dependencies

- Python 3.6

- Selenium 

- OpenCV

- PIL

- Keras

- Chromium driver for Selenium

![gif](https://raw.githubusercontent.com/ravi72munde/Chrome-Dino-Reinforcement-Learning/master/img_data/trained_dino.gif)




# Sample Game Play

https://youtu.be/0oOOqGFmlDs