yenchenlin/DeepLearningFlappyBird

Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).

/ 100

Established

This project lets you observe how a computer program learns to play the game Flappy Bird by itself. It takes the game's screen pixels as input and, through trial and error, learns to make the bird flap at the right time to navigate through pipes. This is ideal for students, researchers, or enthusiasts curious about how artificial intelligence can learn complex tasks without explicit programming.

6,792 stars. No commits in the last 6 months.

Use this if you want to understand or demonstrate a classic example of deep reinforcement learning in action within a familiar game context.

Not ideal if you're looking for a tool to develop or test your own reinforcement learning algorithms, or if you want to play the game yourself.

artificial-intelligence-education reinforcement-learning-demonstration game-AI-study deep-learning-example

Stale 6m No Package No Dependents

Maintenance 0 / 25

Adoption 10 / 25

Maturity 16 / 25

Community 25 / 25

How are scores calculated?

Stars

6,792

Forks

2,065

Language

Python

License

MIT

Compare

DeepLearningFlappyBird and RL-FlappyBird

Related frameworks

ChenglongChen/pytorch-DRL

PyTorch implementations of various Deep Reinforcement Learning (DRL) algorithms for both single...

nikp06/subwAI

Scripts for training an AI to play the endless runner Subway Surfers using a supervised machine...

vladfi1/phillip

The SSBM "Phillip" AI.

kingyuluk/RL-FlappyBird

Using reinforcement learning to train FlappyBird.

vita-epfl/social-nce

[ICCV] Social NCE: Contrastive Learning of Socially-aware Motion Representations

Explore ML Frameworks

All categories Trending ML Framework directory Insights