Sciweavers

513 search results - page 68 / 103
» Finitely Based, Finite Sets of Words
Sort
View
NIPS
2008
15 years 1 months ago
Particle Filter-based Policy Gradient in POMDPs
Our setting is a Partially Observable Markov Decision Process with continuous state, observation and action spaces. Decisions are based on a Particle Filter for estimating the bel...
Pierre-Arnaud Coquelin, Romain Deguest, Rém...
COLOGNETWENTE
2009
15 years 28 days ago
A Simple Linear-Time Recognition Algorithm for Weakly Quasi-Threshold Graphs
: Weakly quasi-threshold graphs form a proper subclass of the well-known class of cographs by restricting the join operation. In this paper we characterize weakly quasi-threshold g...
Stavros D. Nikolopoulos, Charis Papadopoulos
ICML
2010
IEEE
15 years 27 days ago
Feature Selection as a One-Player Game
This paper formalizes Feature Selection as a Reinforcement Learning problem, leading to a provably optimal though intractable selection policy. As a second contribution, this pape...
Romaric Gaudel, Michèle Sebag
IJISEC
2008
119views more  IJISEC 2008»
14 years 11 months ago
Estimating the maximum information leakage
Preventing improper information leaks is a greatest challenge of the modern society. In this paper we present a technique for measuring the ability of several families of adversari...
Alessandro Aldini, Alessandra Di Pierro
LISP
2008
101views more  LISP 2008»
14 years 11 months ago
Flow-sensitive type systems and the ambient calculus
The Ambient Calculus was developed by Cardelli and Gordon as a formal framework to study issues of mobility and migrant code. Numerous analyses have been developed for numerous va...
Torben Amtoft