This paper analyzes the suitability of reinforcement learning (RL) for both programming and adapting situated agents. We discuss two RL algorithms: Q-learning and the Bucket Brigade. We introduce a special case of the Bucket Brigade, and analyze and compare its…

We develop a novel autonomous control synthesis strategy called Phase Space Navigator for the automatic synthesis of nonlinear control systems. The Phase Space Navigator generates global control laws by synthesizing flow shapes of dynamical systems and planning and navigating system…

We develop a qualitative method for understanding and representing phase space structures of complex systems and demonstrate the method with a program, MAPS --- Modeler and Analyzer for Phase Spaces, using deep domain knowledge of dynamical system theory. Given a…

It is obvious to anyone familiar with the rules of the game of chess that a king on an empty board can reach every square. It is true, but not obvious, that a knight can reach every square. Why is…

We describe the automatic synthesis of a global nonlinear controller for stabilizing a magnetic levitation system. The synthesized control system can stabilize the maglev vehicle with large initial displacements from an equilibrium, and possesses a much larger operating region than…

To recognize a previously seen object, the visual system must overcome the variability in the object's appearance caused by factors such as illumination and pose. Developments in computer vision suggest that it may be possible to counter the influence of…

by Henry Neil Holtzman., Thesis (M.S.)--Massachusetts Institute of Technology, Dept. of Architecture, 1991., Includes bibliographical references (leaves 63-66).

(cont.) which is expected, given their additional knowledge resources. The respondents' urgency in looking for the relevant knowledge is the primary explanation for this difference between the two networks. This difference in knowledge networking among the different groups did not…

D. Eleanor Westney., Cover title. "Paper prepared for JAIMS conference on 'International Comparative Study of Knowledge Creation', Hawaii, December 12-14, 1996"--Added t.p. "February 1997.", Includes bibliographical references (p. 31-34).

A system for visual recognition is described, with implications for the general problem of representation of knowledge to assist control. The immediate objective is a computer system that will recognize objects in a visual scene, specifically hammers. The computer receives…