16 search results - page 1 / 4 » Finite-Sample Analysis of LSTD |
ICML
2010
IEEE
13 years 5 months ago
2010
IEEE
In this paper we consider the problem of policy evaluation in reinforcement learning, i.e., learning the value function of a fixed policy, using the least-squares temporal-differe...
TSP
2008
13 years 4 months ago
2008
Abstract--This paper tackles the theoretical performance analysis of widely-linear (WL) multiuser receivers for direct-sequence code-division multiple-access (DS-CDMA) systems, as ...
IJON
2007
13 years 4 months ago
2007
Many algorithms for independent component analysis (ICA) and blind source separation (BSS) can be considered particular instances of a criterion based on the sum of two terms: C(Y...
NIPS
2007
13 years 6 months ago
2007
Over the past few years, the notion of stability in data clustering has received growing attention as a cluster validation criterion in a sample-based framework. However, recent w...
CSDA
2008
13 years 4 months ago
2008
The finite sample properties of the Fourier estimator of integrated volatility under market microstructure noise are studied. Analytic expressions for the bias and the mean square...