John Selinsky

TL;DR: In this paper, a discrete event system (DES) and supervisory control is applied to a power transmission line restoration problem, aiming to increase the steady-state security level of a power network during restoration.

TL;DR: It is suggested and demonstrated that the teacher's knowledge in the supervised learning mode includes a-priori plant sturctural knowledge which may be employed in the design of exploratory schedules during learning that results in an unsupervised learning scheme.

TL;DR: The authors modify an earlier neurocontroller architecture so as to guarantee the performance of the neurocontroller, which uses a priori knowledge of the general structure of the system's dynamics to select subsets of the dynamics.

TL;DR: In this article, the authors explore the relationship of learning and adaptation in robot control and show that learning conflicts with adaptation in its tendency to increase the present tracking error due to the minimization of different criteria (dual control principle).