Adaptive multivariate three-timescale stochastic approximation algorithms for simulation based optimization

DOI10.1145/1044322.1044326zbMath1390.65019OpenAlexW2150152677MaRDI QIDQ4565351

Shalabh Bhatnagar

Publication date: 12 June 2018

Published in: ACM Transactions on Modeling and Computer Simulation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1145/1044322.1044326

zbMATH Keywords

simulation optimizationsimultaneous perturbation stochastic approximationNewton-type algorithmsadaptive stochastic approximation algorithmthree-timescale

Mathematics Subject Classification ID

Probabilistic models, generic numerical methods in probability and statistics (65C20) Numerical optimization and variational techniques (65K10)

Related Items

Multiscale Q-learning with linear function approximation ⋮ A Stochastic Approximation Method for Simulation-Based Quantile Optimization ⋮ A stability criterion for two timescale stochastic approximation schemes ⋮ Variance-constrained actor-critic algorithms for discounted and average reward MDPs ⋮ Monte-Carlo estimation of time-dependent statistical characteristics of random dynamical systems ⋮ Quasi-Newton smoothed functional algorithms for unconstrained and constrained simulation optimization ⋮ Simultaneous perturbation Newton algorithms for simulation optimization ⋮ Simulation optimization: a review of algorithms and applications ⋮ Natural actor-critic algorithms