Pong AI model for dynamic gameplay using ANN evolutionary NEAT optimization

NEAT (NeuroEvolution of Augmenting Topologies) is an evolutionary algorithm that uses genetic evolution approach for creating artificial neural networks. Our work aims at utilizing NEAT in training AI-models by Self-Play Technique to be able to learn the gameplay of Pong and evolving the efficiency of the AI using the NEAT's generational based evolution. Pong is a simple popular indie game making it legible for pattern recognition and AI problem solving studies. Each iteration of the Enhanced AI would reflect the game's difficulty level to the player, determining the level of challenge they would encounter during gameplay. Each successive generation of the evolved AI represents a higher level of gameplay efficiency, allowing it to engage the human players at progressively challenging levels of difficulty. Through this research, we aim to demonstrate the efficiency of combining NEAT with Self-Play for advancing AI capabilities in gaming contexts.