Talendar/flappy-bird-gym

An OpenAI Gym environment for the Flappy Bird game

59
/ 100
Established

This project helps machine learning engineers or researchers train AI agents to play the classic Flappy Bird game. You provide an agent that decides when to flap, and the environment returns either numerical game state data (like bird and pipe positions) or visual RGB images of the game. It's designed for those working with reinforcement learning frameworks to develop and test game-playing AI.

132 stars. No commits in the last 6 months. Available on PyPI.

Use this if you are a machine learning engineer or researcher focused on reinforcement learning and need a simple, well-defined game environment to train and evaluate AI agents.

Not ideal if you are a casual gamer looking to play Flappy Bird, or if you need a complex, high-fidelity game environment for advanced AI research.

reinforcement-learning AI-training game-AI agent-development simulation-environment
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 24 / 25

How are scores calculated?

Stars

132

Forks

94

Language

Python

License

MIT

Last pushed

Feb 14, 2022

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Talendar/flappy-bird-gym"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.