3082 search results - page 44 / 617 » New Bounds for the Controller Problem |
124
click to vote
COLT
2000
Springer
15 years 10 months ago
2000
Springer
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process ( ¢¡¤£¦¥§ ), and focus on gradient ascent approache...
134
click to vote
INFOCOM
2003
IEEE
15 years 11 months ago
2003
IEEE
—This paper is aimed at designing a congestion control system that scales gracefully with network capacity, providing high utilization, low queueing delay, dynamic stability, and...
170
click to vote
AAAI
2006
15 years 7 months ago
2006
We present a new formulation of distributed task assignment, called Generalized Mutual Assignment Problem (GMAP), which is derived from an NP-hard combinatorial optimization probl...
160
Voted
TCS
2010
15 years 4 months ago
2010
We study non-uniform constraint satisfaction problems definable in monadic Datalog stratified by the use of non-linearity. We show how such problems can be described in terms of...
163
Voted
SODA
2010
ACM
15 years 3 months ago
2010
ACM
Differential privacy is a recent notion of privacy tailored to the problem of statistical disclosure control: how to release statistical information about a set of people without ...