Machine learning - balancing a stack of balls
A genetic algorithm is used to train a neural network controller to balance a stack of balls.
You are now following this Submission
- You will see updates in your followed content feed
- You may receive emails, depending on your communication preferences
A genetic algorithm is used to train a neural network controller to balance a stack of balls by applying a lateral force and a torque to the bottom ball. The capsim physics engine is used to produce a realistic simulation for each attempt. It can learn up to 4 balls.
http://www.youtube.com/watch?v=c4vADjwOFNc
Cite As
Peter Bone (2026). Machine learning - balancing a stack of balls (https://www.mathworks.com/matlabcentral/fileexchange/36911-machine-learning-balancing-a-stack-of-balls), MATLAB Central File Exchange. Retrieved .
Acknowledgements
Inspired by: CapSim - the MATLAB physics engine, export_fig
Inspired: Machine learning - PushBall game
General Information
- Version 1.2.0.0 (48.7 KB)
MATLAB Release Compatibility
- Compatible with any release
Platform Compatibility
- Windows
- macOS
- Linux
