cpury/pong-rl

Reinforcement Learning with Pong in the Browser via TensorFlow.js

27
/ 100
Experimental

This project lets you observe a computer program learn to play the classic game Pong in a web browser. You can watch it play against itself, with one side controlled by a Deep Q-Learning algorithm that learns from game features or directly from the screen pixels. This is for anyone curious about how artificial intelligence, specifically reinforcement learning, can 'learn' a task through trial and error.

No commits in the last 6 months.

Use this if you want to visually demonstrate or understand the basics of reinforcement learning in a fun, interactive game environment.

Not ideal if you're looking for a cutting-edge AI research tool or a high-performance gaming application.

artificial-intelligence machine-learning-demonstration educational-tool reinforcement-learning game-ai
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

17

Forks

1

Language

JavaScript

License

MIT

Last pushed

Jan 04, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cpury/pong-rl"

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