Machine-Learning-Flappy-Bird and floppy-bird
These are competitors offering alternative approaches to the same problem: both implement AI agents that learn to play Flappy Bird, with A using a genetic algorithm and B using Q-learning and NEAT, allowing developers to choose their preferred reinforcement learning or evolutionary strategy.
About Machine-Learning-Flappy-Bird
ssusnic/Machine-Learning-Flappy-Bird
Machine Learning for Flappy Bird using Neural Network and Genetic Algorithm
Implements neuro-evolution by combining a 3-layer neural network (2 input neurons sensing gap distance/height, 6 hidden neurons, 1 output neuron) with a genetic algorithm that performs selection, crossover, and mutation across generations. Built entirely in HTML5 using the Phaser game framework and Synaptic neural network library, with fitness calculated as distance traveled minus proximity to obstacles.
About floppy-bird
thomas-bouvier/floppy-bird
Flappy Bird-like game including a Q-learning algorithm and a neural network-based algorithm (NEAT) for artificial intelligence
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work