E. Hyytiä and J. Virtamo, Optimal Importance Sampling in Markov Process Simulation, in International Conference on Applied Simulation and Modelling, ASM 2001, pp. 67-72, 2001, Marbella, Spain.
Abstract: In this paper we present an adaptive algorithm to estimate the transient blocking probability of a communication system, described by a Markov process, during a finite time interval starting from a given state. The method uses importance sampling for variance reduction and adjusts the parameters of the twisted distribution based on earlier samples. The method can be effectively applied to a decision making problem where future revenues are estimated with extensive simulations, in order to find an improved policy by so called first policy iteration.
Links:
BibTeX entry:
@inproceedings{hyytia-asm-2001,
author = {Esa Hyyti{\"a} and Jorma Virtamo},
title = {Optimal Importance Sampling in {Markov} Process Simulation},
booktitle = {International Conference on Applied Simulation and Modelling, {ASM} 2001},
address = {Marbella, Spain},
editors = {M. H. Hamza},
year = {2001},
month = {Sep.},
pages = {67--72}
}