DmpBbo: A versatile Python/C++ library for Function Approximation, Dynamical Movement Primitives, and Black-Box Optimization

Dynamical movement primitives (DMPs) are one of the most popular representations for goal-directed motion primitives in robotics. They are also often used as the policy representation for policy improvement in robotics, a particular form of reinforcement learning. dmpbbo provides five software modules for the representation and optimization of dynamical movement primitives.