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.
Peter Bone (2019). 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 .
Inspired: Machine learning - PushBall game