Skip to content

lsig/QLearningFlappyBird

Repository files navigation

Q-Learning and Deep-Q-Learning for FlappyBird

This repository contains two different machine learning models for learning flappy bird.

Q-Learning

There are two different Q-Learning classes, one simple with a fixed learning rate and a fixed epsilon. The other class implements learning rate decay and epsilon decay for greater configuration. Surprisingly Q-Learning beats out the Deep-Q-Learning neural network.

Deep-Q-Learning

The Deep-Q-Learning class is extremely configurable and easy to finetune for different needs. The network architecture is isolated in the network script, and tuning the hyperparameters is done the deep_q_learning script.

Report

For greater detail you can find a pdf report in the repository which explains the project and its results.

Happy Flapping!

About

QLearning and Deep-QLearning models for FlappyBird

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages