The pong game is one of the earliest computer games. It is based on table tennis sports. The goal of the game is to defeat the opponent by earning a higher score. The game can be played by two human players, or one player against a computer. A player controls a game paddle at one end of the screen, and the opponent on the opposite end. The paddle is used to hit the pong ball. Points are scored when one is able to prevent another to return the ball.
In this research, NeuraBASE is used to position the paddle in the correct position to prevent the opponent from scoring. A 2D (two-dimensional) version of the game is developed in the early phase, in which NeuraBASE controllers for horizontal and vertical movements of the paddle are developed separately. Then, these controllers are combined as a joint controller for a 3D (three-dimensional) version of the game. The objective of this research is to demonstrate the feasibility of using NeuraBASE as an artificial intelligence in a game. This approach allows independent controllers to be combined in a linear rather than exponential fashion, thus reducing model complexity.
A pong game performed by a neuromorphic chip built by SyNAPSE researchers at IBM.