Machine learning - balancing a stack of balls
A genetic algorithm is used to train a neural network controller to balance a stack of balls.
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
引用格式
Peter Bone (2026). Machine learning - balancing a stack of balls (https://ww2.mathworks.cn/matlabcentral/fileexchange/36911-machine-learning-balancing-a-stack-of-balls), MATLAB Central File Exchange. 检索时间: .
