Abstract: A reward function estimated with inverse reinforcement learning has been used to determine a method for controlling a robot. Inverse reinforcement learning requires observed sequences of ...

Zoom is a display tool that expands the view of the selected waveform. The source trace can be expanded horizontally and vertically for detailed visual analysis or further processing. Each zoom trace ...

Abstract: Opacity of a discrete event system is a confidentiality property that characterizes instances when the secret behavior of the system cannot be revealed. This paper considers current-state ...