Learning stabilizable nonlinear dynamics with contraction-based regularization
Learning stabilizable nonlinear dynamics with contraction-based regularization
We propose a novel framework for learning stabilizable nonlinear dynamical systems for continuous control tasks in robotics. The key contribution is a control-theoretic regularizer for dynamics fitting rooted in the notion of stabilizability, a constraint which guarantees the existence of robust tracking controllers for arbitrary open-loop trajectories generated with the …