Two-timescale simultaneous perturbation stochastic approximation using deterministic perturbation sequences
DOI10.1145/858481.858486zbMATH Open1390.65045OpenAlexW2125852847MaRDI QIDQ4564833FDOQ4564833
Authors: Shalabh Bhatnagar, Michael C. Fu, Steven I. Marcus, I-Jeng Wang 
Publication date: 12 June 2018
Published in: ACM Transactions on Modeling and Computer Simulation (Search for Journal in Brave)
Full work available at URL: http://eprints.iisc.ac.in/266/1/p180-bhatnagar.pdf
Recommendations
- Stochastic approximation with two time scales
- Nonlinear Two-Time-Scale Stochastic Approximation: Convergence and Finite-Time Performance
- A stability criterion for two timescale stochastic approximation schemes
- A two Timescale Stochastic Approximation Scheme for Simulation-Based Parametric Optimization
- Simultaneous perturbation stochastic approximation: towards one-measurement per iteration
- Simultaneous perturbation stochastic approximation of nonsmooth functions
- Adaptive stochastic approximation by the simultaneous perturbation method
- scientific article; zbMATH DE number 1383146
stochastic approximationHadamard matricessimulation optimizationSPSAtwo-timescale algorithmsdeterministic perturbations
Numerical optimization and variational techniques (65K10) Probabilistic models, generic numerical methods in probability and statistics (65C20)
Cited In (17)
- Optimal design of structures using the simultaneous perturbation stochastic approximation algorithm
- Convergence rate of moments in stochastic approximation with simultaneous perturbation gradient approximation and resetting
- Variance-constrained actor-critic algorithms for discounted and average reward MDPs
- Actor-critic algorithms for hierarchical Markov decision processes
- An adaptive optimization scheme with satisfactory transient performance
- Adaptive multivariate three-timescale stochastic approximation algorithms for simulation based optimization
- Nonlinear conjugate gradient method based SPSA
- A stability criterion for two timescale stochastic approximation schemes
- Multiscale Q-learning with linear function approximation
- Simultaneous perturbation Newton algorithms for simulation optimization
- Weak convergence of dynamical systems in two timescales
- Parallel simultaneous perturbation optimization
- Optimal random perturbations for stochastic approximation using a simultaneous perturbation gradient approximation
- A simultaneous perturbation stochastic approximation algorithm based on quasi-Newton method
- Performance analysis of the simultaneous perturbation stochastic approximation algorithm on the noisy sphere model
- Revisiting the ODE method for recursive algorithms: fast convergence using quasi stochastic approximation
- New algorithms of the Q-learning type
This page was built for publication: Two-timescale simultaneous perturbation stochastic approximation using deterministic perturbation sequences
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4564833)
