Sciweavers

236 search results - page 3 / 48
» Bias and Variance Approximation in Value Function Estimates
Sort
View
COLT
2000
Springer
13 years 11 months ago
Bias-Variance Error Bounds for Temporal Difference Updates
We give the first rigorous upper bounds on the error of temporal difference (td) algorithms for policy evaluation as a function of the amount of experience. These upper bounds pr...
Michael J. Kearns, Satinder P. Singh
WSC
2007
13 years 9 months ago
Replicated batch means for steady-state simulations with initial transients
We provide asymptotic expressions for the expected value and variance of the replicated batch means variance estimator when the stochastic process being simulated has an additive ...
Christos Alexopoulos, Sigrún Andradó...
ANSS
1996
IEEE
13 years 11 months ago
Computation of the Asymptotic Bias and Variance for Simulation of Markov Reward Models
The asymptotic bias and variance are important determinants of the quality of a simulation run. In particular, the asymptotic bias can be used to approximate the bias introduced b...
Aad P. A. van Moorsel, Latha A. Kant, William H. S...
WSC
2007
13 years 9 months ago
Low bias integrated path estimators
We consider the problem of estimating the time-average variance constant for a stationary process. A previous paper described an approach based on multiple integrations of the sim...
James M. Calvin
FSTTCS
2009
Springer
14 years 2 months ago
Functionally Private Approximations of Negligibly-Biased Estimators
ABSTRACT. We study functionally private approximations. An approximation function g is functionally private with respect to f if, for any input x, g(x) reveals no more information ...
André Madeira, S. Muthukrishnan