Skip to content

Implemented neural network which learns to play flappy bird through Neuroevolution with fixed topologies from scratch.

Notifications You must be signed in to change notification settings

ayushdiagarwal/Flapp

Folders and files

NameName
Last commit message
Last commit date

Latest commit

fb0f8d7 · Jul 16, 2024

History

19 Commits
Jul 16, 2024
Jul 14, 2024
Jul 13, 2024
Jul 16, 2024
Jul 16, 2024
Jul 16, 2024

Repository files navigation

Reinforcement Learning Flappy Bird (From Scratch)

This is an implementation of reinforcement learning which learns to play Flappy bird game which utilises Neuroevolution with fixed topologies to enable the neural network to learn to play the game. However, this is still in development stage and I couldn't get the neural net to learn properly.

How it works

Neural Network

This game uses the simplest neural network which is called a Perceptron.

Perceptron

Neuroevolution

Neuroevolution involves evolving neural networks using genetic algorithms. Here’s a brief overview of the process.

Neuroevolution

About

Implemented neural network which learns to play flappy bird through Neuroevolution with fixed topologies from scratch.

Resources

Stars

Watchers

Forks

Languages