pawel-kieliszczyk/snake-reinforcement-learning

AI (A2C agent) mastering the game of Snake with TensorFlow 2.0

25
/ 100
Experimental

This project helps AI researchers and students train an AI agent to master the classic game of Snake. By applying reinforcement learning, specifically a distributed A2C algorithm, it takes raw pixel data from the game as input and outputs a highly skilled AI that can achieve maximum scores. It's designed for anyone exploring or implementing reinforcement learning techniques.

No commits in the last 6 months.

Use this if you are a researcher or student looking for a concrete example and implementation of an A2C reinforcement learning agent applied to a game from pixel inputs.

Not ideal if you're looking for a general-purpose reinforcement learning library or a tool for playing Snake yourself.

reinforcement-learning AI-training game-AI deep-learning-examples agent-training
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

41

Forks

4

Language

Python

License

Category

snake-game-ai

Last pushed

Jul 21, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pawel-kieliszczyk/snake-reinforcement-learning"

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