purusharth07 / ping-pong-neural-game- Goto Github PK
View Code? Open in Web Editor NEWPing-Pong game developed using Python 'pygame'. The game developed is a self learning game which consists of two Halves: 1.)First half is actually computer itself playing whereas 2.) Second half is our learning AI that learns and enhance itself slowly and slowly with time. Self-Learning is done with the help of Deep Q Network that gets better and better over time through trial and error. The DQN is a convolutional neural network that reads in pixel data from the game and the game score. Using just those 2 parameters, it learns what moves it needs to make to become better.