foersterrobert / DQpoNg

Use the movements of your thumb to play Pong against a pre-trained Double-DQN-Agent. I used Google-Colab for training the pyTorch model and created the Pong environment with Pygame.

Double-DQN for Pong

requirements:

torch==1.9.0
numpy==1.21.3
pygame==2.0.1
mediapipe==0.8.9
opencv-python==4.5.3.56

useful resources:

• DQN-Paper Explained: https://www.youtube.com/watch?v=H1NRNGiS8YU
• DQN-Paper: https://storage.googleapis.com/deepmind-media/dqn/DQNNaturePaper.pdf
• Double-DQN Explained: https://www.youtube.com/watch?v=ILDLT97FsNM
• Double-DQN Paper: https://arxiv.org/pdf/1509.06461.pdf
• DQN in PyTorch: https://www.youtube.com/watch?v=NP8pXZdU-5U