kingyuluk/RL-FlappyBird
Using reinforcement learning to train FlappyBird.
This project allows developers to experiment with reinforcement learning by training an AI to play Flappy Bird. You provide the game environment and the learning algorithm, and the project outputs a trained model that can autonomously navigate the bird through obstacles. It's designed for machine learning practitioners interested in practical applications of Deep Q-Networks.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher wanting to see a concrete example of Deep Reinforcement Learning applied to a classic game environment.
Not ideal if you're looking for a general-purpose reinforcement learning framework or a tool for real-world automation outside of game AI.
Stars
82
Forks
27
Language
Java
License
MIT
Category
Last pushed
Dec 04, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kingyuluk/RL-FlappyBird"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yenchenlin/DeepLearningFlappyBird
Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).
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.
vita-epfl/social-nce
[ICCV] Social NCE: Contrastive Learning of Socially-aware Motion Representations