Linear Convergence of a Policy Gradient Method for Some Finite Horizon Continuous Time Control Problems (Q6140987): Difference between revisions

Latest revision as of 18:49, 30 December 2024

scientific article; zbMATH DE number 7782638

Language	Label	Description	Also known as
English	Linear Convergence of a Policy Gradient Method for Some Finite Horizon Continuous Time Control Problems	scientific article; zbMATH DE number 7782638

Statements

instance of

scholarly article

0 references

title

Linear Convergence of a Policy Gradient Method for Some Finite Horizon Continuous Time Control Problems (English)

0 references

0 references

0 references

0 references

SIAM Journal on Control and Optimization

0 references

publication date

2 January 2024

0 references

full work available at URL

https://arxiv.org/abs/2203.11758

0 references

zbMATH Keywords

reinforcement learning

0 references

policy gradient method

0 references

stochastic control

0 references

linear convergence

0 references

stationary point

0 references

backward stochastic differential equation

0 references

MaRDI profile type

MaRDI publication profile

0 references

cites work

Convexity and Optimization in Banach Spaces

0 references

On the convergence rate of approximation schemes for Hamilton-Jacobi-Bellman Equations

0 references

A Numerical Scheme for a Mean Field Game in Some Queueing Systems Based on Markov Chain Approximation Method

0 references

A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems

0 references

Time discretization and Markovian iteration for coupled FBSDEs

0 references

Mean Field Games and Mean Field Type Control Theory

0 references

BSDEs with polynomial growth generators

0 references

Q2807034

0 references

A regression-based Monte Carlo method to solve backward stochastic differential equations

0 references

Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon

0 references

Solving high-dimensional partial differential equations using deep learning

0 references

Deep backward schemes for high-dimensional nonlinear PDEs

0 references

Nonlinear control systems: An introduction

0 references

A neural network-based policy iteration algorithm with global \(H^2\)-superlinear convergence for stochastic games on domains

0 references

Exponential Convergence and Stability of Howard's Policy Improvement Algorithm for Controlled Diffusions

0 references

A modified MSA for stochastic control problems

0 references

Q2703816

0 references

Q4558489

0 references

Time discretization of FBSDE with polynomial growth drivers and reaction-diffusion PDEs

0 references

Sufficient stochastic maximum principle for discounted control problem

0 references

Q3093369

0 references

Introductory lectures on convex optimization. A basic course.

0 references

Q4379369

0 references

Continuous-time stochastic control and optimization with financial applications

0 references

Variational Analysis

0 references

Q4626283

0 references

Backward Stochastic Differential Equations

0 references

Identifiers

arXiv ID

2203.11758

0 references

Mathematics Subject Classification ID

0 references

0 references

0 references

0 references

0 references

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:6140987

@@ Property / DOI @@
-.1137/22m1492180
@@ Property / DOI: 10.1137/22m1492180 / rank @@
-Normal rank
@@ Property / cites work @@
+Convexity and Optimization in Banach Spaces
@@ Property / cites work: Convexity and Optimization in Banach Spaces / rank @@
+Normal rank
@@ Property / cites work @@
+On the convergence rate of approximation schemes for Hamilton-Jacobi-Bellman Equations
+Normal rank
@@ Property / cites work @@
+A Numerical Scheme for a Mean Field Game in Some Queueing Systems Based on Markov Chain Approximation Method
+Normal rank
@@ Property / cites work @@
+A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
+Normal rank
@@ Property / cites work @@
+Time discretization and Markovian iteration for coupled FBSDEs
+Normal rank
@@ Property / cites work @@
+Mean Field Games and Mean Field Type Control Theory
+Normal rank
@@ Property / cites work @@
+BSDEs with polynomial growth generators
@@ Property / cites work: BSDEs with polynomial growth generators / rank @@
+Normal rank
@@ Property / cites work @@
+Q2807034
@@ Property / cites work: Q2807034 / rank @@
+Normal rank
@@ Property / cites work @@
+A regression-based Monte Carlo method to solve backward stochastic differential equations
+Normal rank
@@ Property / cites work @@
+Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon
+Normal rank
@@ Property / cites work @@
+Solving high-dimensional partial differential equations using deep learning
+Normal rank
@@ Property / cites work @@
+Deep backward schemes for high-dimensional nonlinear PDEs
+Normal rank
@@ Property / cites work @@
+Nonlinear control systems: An introduction
@@ Property / cites work: Nonlinear control systems: An introduction / rank @@
+Normal rank
@@ Property / cites work @@
+A neural network-based policy iteration algorithm with global \(H^2\)-superlinear convergence for stochastic games on domains
+Normal rank
@@ Property / cites work @@
+Exponential Convergence and Stability of Howard's Policy Improvement Algorithm for Controlled Diffusions
+Normal rank
@@ Property / cites work @@
+A modified MSA for stochastic control problems
@@ Property / cites work: A modified MSA for stochastic control problems / rank @@
+Normal rank
@@ Property / cites work @@
+Q2703816
@@ Property / cites work: Q2703816 / rank @@
+Normal rank
@@ Property / cites work @@
+Q4558489
@@ Property / cites work: Q4558489 / rank @@
+Normal rank
@@ Property / cites work @@
+Time discretization of FBSDE with polynomial growth drivers and reaction-diffusion PDEs
+Normal rank
@@ Property / cites work @@
+Sufficient stochastic maximum principle for discounted control problem
+Normal rank
@@ Property / cites work @@
+Q3093369
@@ Property / cites work: Q3093369 / rank @@
+Normal rank
@@ Property / cites work @@
+Introductory lectures on convex optimization. A basic course.
+Normal rank
@@ Property / cites work @@
+Q4379369
@@ Property / cites work: Q4379369 / rank @@
+Normal rank
@@ Property / cites work @@
+Continuous-time stochastic control and optimization with financial applications
+Normal rank
@@ Property / cites work @@
+Variational Analysis
@@ Property / cites work: Variational Analysis / rank @@
+Normal rank
@@ Property / cites work @@
+Q4626283
@@ Property / cites work: Q4626283 / rank @@
+Normal rank
@@ Property / cites work @@
+Backward Stochastic Differential Equations
@@ Property / cites work: Backward Stochastic Differential Equations / rank @@
+Normal rank
@@ Property / DOI @@
+.1137/22M1492180
@@ Property / DOI: 10.1137/22M1492180 / rank @@
+Normal rank