[PYTORCH] Deep Q-learning for playing Chrome Dino

Introduction

Here is my python source code for training an agent to play flappy bird. It could be seen as a very basic example of Reinforcement Learning's application.

Result

The corresponding output video will also be generated and stored by default at output/chrome_dino.mp4

Output video

How to use my code

With my code, you can:

• Train your model from scratch by running python train.py
• Test your trained model by running python test.py

Trained models

You could find my trained model at trained_models/chrome_dino.pth

Requirements

• python 3.6
• pygame
• cv2
• pytorch
• numpy

Reference

• https://github.com/shivamshekhar/Chrome-T-Rex-Rush: My environment is based on this great repository.