We develop a hybrid control approach for robot learning based on combining learned predictive models with experience-based state-action policy mappings to improve the capabilities of robotic systems. Predictive provide an understanding task and physics (which improves sample-efficiency), while are treated as “muscle memory” that encode favorable actions experiences override planned actions. Hyb...

Hybrid control systems, that is, systems which contain both continuous dynamics and discrete event dynamics are studied in this paper. First, a model is introduced that describes the continuous plant and discrete event controller along with an interface which connects them. A Discrete Event System (DES) automaton description is employed to describe the plant together with the interface and it i...