Skip to content

Latest commit

 

History

History
27 lines (21 loc) · 881 Bytes

README.md

File metadata and controls

27 lines (21 loc) · 881 Bytes

QLearning-Self-Driving-Car-Game

Self Driving Car game automated with "Reinforcement Deep Q-Learning"

How to start?

  1. Install the required libraries on your Conda env :
(Use Python >= v3.5)

For linux/Mac users :
conda install pytorch==0.3.1 -c pytorch
conda install -c conda-forge kivy

For Windows users : 
conda install -c peterjc123 pytorch-cpu
conda install -c conda-forge kivy
  1. Run the map.py file in your Bash-terminal/Powershell as python map.py
  2. Click on the load button to load your saved checkpoint last_train_brain.pth (file in the repo) ....and you're all set!

You can do more hyperparameter tuning or change the reward values for the car in the my_ai.py!

Youtube Link

Self Driving Car Game with Deep Q-Learning

Developer

Harsh Soni