Please Share, Subscribe or check out my website below! Here I have a demo of a Machine Learning Algorithm for Flappy Birds using Neural Network and Genetic Algorithm. Except I went ahead and used a usb web server to drive the program for portability and lightweight purposes for testing!
The birds are basically trying to get through the gap/space for each set of trees- and you watch the optimization occur during the regenerative natural selection process. The goal is to get all the way through the gaps/slots. You can see improvement throughout the video progression.
The magic behind this ML? An artificial neural network is a subset of machine learning algorithm. It is inspired by the structure and functions of biological neural networks. These networks are made out of many neurons which send signals to each other. A genetic algorithm is used to train and improve neural networks. A fitness function is defined in this demo as the difference between the total distance covered by a bird and its current distance to the closest gap. Thus the fitness function is essentially for distance measurement/metric- to aid in the natural selection process.
According to Wikipedia:
Genetic algorithms are commonly used to generate high-quality solutions to optimization and search problems by relying on bio-inspired operators such as mutation, crossover and selection.
Credit Goes Out To: Srdjan Susnic
Original Video That Inspired Me to try It Out:
My Website: &