thomasbi1/cyberrunner

CyberRunner is an AI robot whose task is to learn how to play the popular and widely accessible labyrinth marble game.

38
/ 100
Emerging

This project helps robotics enthusiasts and AI researchers build a robot that can learn to play the classic labyrinth marble game on its own. It takes camera observations of the game and outputs motor commands to tilt the board, allowing the robot to improve its game strategy continuously and quickly beat human players. Robotics hobbyists, students, and AI researchers interested in practical reinforcement learning applications would use this.

121 stars. No commits in the last 6 months.

Use this if you want to build and experiment with an AI-powered physical robot that learns complex motor control tasks through trial and error in a real-world setting.

Not ideal if you're looking for a pre-built, ready-to-play robot game or a purely software-based simulation.

robotics reinforcement-learning mechatronics AI-education automation-experiments
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

121

Forks

8

Language

Python

License

AGPL-3.0

Category

godot-game-ai

Last pushed

Oct 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/thomasbi1/cyberrunner"

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