8 search results - page 1 / 2 » Q-learning and Pontryagin's Minimum Principle |
CDC
2009
IEEE
13 years 10 months ago
2009
IEEE
Abstract— Q-learning is a technique used to compute an optimal policy for a controlled Markov chain based on observations of the system controlled using a non-optimal policy. It ...
SIAMCO
2000
13 years 5 months ago
2000
This paper deals with optimal control problems of semilinear parabolic equations with pointwise state constraints and coupled integral state-control constraints. We obtain necessar...
AUTOMATICA
2008
13 years 5 months ago
2008
In this paper we address the problem of optimal switching for switched linear systems. The uniqueness of our approach lies in describing the switching action by multiple control i...
ICRA
2007
IEEE
13 years 11 months ago
2007
IEEE
— Computing optimal paths for mobile robots is an interesting and important problem. This paper presents a method to compute the shortest path for a differential-drive mobile rob...
ICRA
2006
IEEE
13 years 11 months ago
2006
IEEE
— Characterizing optimal paths for mobile robots is an interesting, important, and challenging endeavor. Not only they are interesting with respect to the optimized criteria, but...