In this work, we present a unified, general approach to variance reduction in agent evaluation using machine learning to minimize variance. Evaluating an agent’s performance in a stochastic setting is necessary for agent development, scientific evaluation, and competitions. Traditionally, evaluation is done using Monte Carlo estimation (sample averages); the magnitude of the stochasticity in th...

Performability modelling has been most successfully applied for gracefully degradable computer systems by using Markov reward models [2]. In this approach the relation of the performability model with the underlying performance and dependability model is exploited. For many systems and for many measures of interest this type of modelling is not suited, so another performability modelling approa...

This article revisits the Diffusion Operator Integral (DOI) variance reduction technique originally proposed in Heath and Platen (2002) extends its theoretical concept to pricing of America...

In this short paper a new technique, called Fault Injection Simulation (FIS), is discussed that is suited for deriving results for steady-state measures in discrete event dynamic systems which are strongly influenced by rarely occurring events. FIS is based on division of the observations in those that are affected and those that are not affected by these rare events. If methods are available F...

reliability evaluation of a large-scale composite power system faces to numerous events/outage and consequently imposes an extensive burden of calculations. in order to simplify the problem, determination of an equivalent system for large-scale power system is inevitable. this paper proposes a framework as reduction technique to separate a composite power system to three areas: external area, o...