TimHanewich/tetris-ai-mini

Training a neural network (AI) to play a very simplified game of 4x4 Tetris using Q-Learning.

28
/ 100
Experimental

This project helps demonstrate how to train an AI agent to play a very simplified 4x4 Tetris game using Q-Learning, a reinforcement learning technique. It takes game board states as input and outputs optimal moves the AI should make. Researchers and students exploring reinforcement learning or AI development would find this useful for understanding basic AI training principles.

No commits in the last 6 months.

Use this if you are a student or researcher wanting a simple, clear example of reinforcement learning in action to understand how an AI learns to make decisions in a game.

Not ideal if you are looking for a complex AI solution for real-world strategic games or a production-ready game AI.

AI-training reinforcement-learning game-AI Q-learning neural-networks
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Python

License

MIT

Category

tetris-ai-agents

Last pushed

Dec 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/TimHanewich/tetris-ai-mini"

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