Project to pratice Pytorch
python3 -m venv venv
source venv/bin/activate
pip3 install -r requirements.txt
python3 main.py
Select two of the below players with ENTER
player | implementation | description |
---|---|---|
Human | PlayerHuman.py | Control with A and Z or Up and Down |
Artificial Intelligence | PlayerAI.py | Keep the player in the same horizontal position of the ball when it is coming |
Neural Network DQL | PlayerNN.py | Execution of Neural Network Deep Q-Learning |
Neural Network DQL Training | PlayerNN.py | Training of Neural Network Deep Q-Learning |
-
This model was trained for approximately 100 hours.
-
Had to restart a few times to get back to training from a reasonable solution.
-
So far I haven't managed to make NN beat simple programming logic 100% of the time!
Reference Code: https://github.com/python-engineer/snake-ai-pytorch
Reference Tutorial: https://www.youtube.com/watch?v=PJl4iabBEz0
pip freeze > requirements.txt