Stochastic recursive algorithms for optimization. Simultaneous perturbation methods

DOI10.1007/978-1-4471-4285-0zbMath1260.90002MaRDI QIDQ441138

H. L. Prasad, L. A. Prashanth, Shalabh Bhatnagar

Publication date: 20 August 2012

Published in: Lecture Notes in Control and Information Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-1-4471-4285-0

zbMATH Keywords

Markov decision process; gradient schemes; algorithms of Robbins-Monro and Kiefer-Wolfowitz; stochastic recursive algorithms

Mathematics Subject Classification ID

90C20: Quadratic programming

90B36: Stochastic scheduling theory in operations research

90C40: Markov and semi-Markov decision processes

90B20: Traffic problems in operations research

90-02: Research exposition (monographs, survey articles) pertaining to operations research and mathematical programming

Related Items

Risk-Constrained Reinforcement Learning with Percentile Risk Criteria, Iterative learning control using faded measurements without system information: a gradient estimation approach, Gradient-Based Adaptive Stochastic Search for Simulation Optimization Over Continuous Space, A simulation‐based algorithm for optimal pricing policy under demand uncertainty, Derivative-free optimization methods, Actor-Critic Algorithms with Online Feature Adaptation, Multiscale Q-learning with linear function approximation, Newton-based stochastic optimization using \(q\)-Gaussian smoothed functional algorithms, Quasi-Newton smoothed functional algorithms for unconstrained and constrained simulation optimization, Variance-constrained actor-critic algorithms for discounted and average reward MDPs, Nested kriging predictions for datasets with a large number of observations, Generalization of a result of Fabian on the asymptotic normality of stochastic approximation, Recurrent neural networks as optimal mesh refinement strategies, Simulation methods for robust risk assessment and the distorted mix approach, Smoothed functional-based gradient algorithms for off-policy reinforcement learning: a non-asymptotic viewpoint, Simultaneous perturbation Newton algorithms for simulation optimization