SPSC: a new execution policy for exploring discrete-time stochastic simulations

TL;DR

This paper presents SPSC, a novel execution policy designed to efficiently estimate solution probabilities in stochastic simulations, especially effective for multi-agent-based simulations, outperforming traditional Monte Carlo methods.

Contribution

The paper introduces SPSC, a new simulation execution policy that improves probability estimation efficiency in stochastic simulations, with a focus on multi-agent systems.

Findings

SPSC outperforms Monte Carlo in efficiency for MABS.

SPSC is adaptable to various types of stochastic simulations.

The method provides accurate probability estimates with fewer simulations.

Abstract

In this paper, we introduce a new method called SPSC (Simulation, Partitioning, Selection, Cloning) to estimate efficiently the probability of possible solutions in stochastic simulations. This method can be applied to any type of simulation, however it is particularly suitable for multi-agent-based simulations (MABS). Therefore, its performance is evaluated on a well-known MABS and compared to the classical approach, i.e., Monte Carlo.