Skip to content

devaar100/RL-FlapPyBird

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Reinforcement Learning Flappy Bird Bot

This bot learns via Q-Learning with every move made

alt text

Working

With every move made, the bird observes the state it was in, and the action it took. With regards to their outcomes, it punishes or rewards the state-action pairs. After playing the game numerous times, the bird is able to consistently obtain high scores.

A reinforcement learning algorithm called Q-learning is utilized. This project is heavily influenced by the very well documented work of harvitronix. I was able to implement the concepts learned on modified version of FlapPyBird by sourabhv.

The purpose of this project is to eventually use the learnings from the game to operate a real-life remote-control car, using distance sensors. This version of the code attempts to simulate the use of sensors to get us a step closer to being able to use this in the real world.

About

Reinforcement Learning based FlapPyBird Bot

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published