The intent of this work is to explore the interactions of artificial neural networks and digital games. It details the development of an artificial neural network trained upon a brick breaking game like the Atari game Breakout. This network was designed with the goals of not dropping the ball and maximizing the game score. Full game and network integration was not completed. However, two versions of the network were developed to move the paddle to the right or left based on the ball's point of impact on the paddle. In preliminary testing using manual inputs, these networks eventually learned to return the expected output 100 percent of the time. Next steps in the development of this neural network include the addition of multiple inputs, the ability to output a distance for the paddle to move, and full integration with the brick breaking game.
"A Collaboration between Neural Networks and Reinforcement Learning: Applying Concepts to a Brick Breaking Game,"
Augsburg Honors Review: Vol. 10
, Article 5.
Available at: https://idun.augsburg.edu/honors_review/vol10/iss1/5