000paradox000/snake_rl

Snake RL: A pedagogical project to begin Reinforcement Learning

Snake RL is a simple project that implements Proximal Policy Optimization to train a model play a simple Snake game created with pygame.

How It Works

First create a virtual environment (python 3.11) and install the requirements.

1. Play Snake Yourself Run the following command python main.py
2. Train a Model Run the following command python train.py
3. Make the Model Play Run the following command python model_play.py once a model have been trained

https://www.linkedin.com/feed/update/urn:li:activity:7162421302249656320?utm_source=share&utm_medium=member_desktop https://github.com/alberto-molinaro/snake_rl