Name		Name	Last commit message	Last commit date
Latest commit History 27 Commits
tools		tools
Environment_Setup.ipynb		Environment_Setup.ipynb
Model_Testing.ipynb		Model_Testing.ipynb
Model_Training.ipynb		Model_Training.ipynb
README.md		README.md

Repository files navigation

FlappyBird-ReinforcmentLearning

Creating agent that can play FlappyBird in browser using DQN algorythm.

Links to the games with no ads:

very easy environment: https://scratch.mit.edu/projects/40001012/fullscreen/
easy environment: https://scratch.mit.edu/projects/36195342/fullscreen/
medium environment: https://scratch.mit.edu/projects/25828661/fullscreen/
hard environment: https://scratch.mit.edu/projects/17828009/fullscreen/

About

This project implements an agent for playing the FlappyBird game in a browser using the Deep Q-Network (DQN) algorithm from the stablebaselines3 library. The agent is trained to learn the optimal actions to take at each step in the game in order to maximize the score.

game python browser reinforcement-learning dqn flappybird stable-baselines3

Report repository

Releases

No releases published

Packages

Contributors

Languages