A simpler method for learning to control a robot

One way to think about this structure is as a hint that can help guide how to control a system. This could help their learning-based control system achieve better performance faster in rapidly changing environments. Learning a controllerDetermining the best way to control a robot to accomplish a given task can be a difficult problem, even when researchers know how to model everything about the system. “We found that beyond learning the dynamics, it’s also essential to learn the control-oriented structure that supports effective controller design. The result is a data-efficient learning process that outputs dynamic models that enjoy intrinsic structure that enables effective, stable, and robust control.