Multiply Accelerated Value Iteration for NonSymmetric Affine Fixed Point Problems and Application to Markov Decision Processes (Q5862806): Difference between revisions

Latest revision as of 09:11, 30 July 2024

scientific article; zbMATH DE number 7487114

Language	Label	Description	Also known as
English	Multiply Accelerated Value Iteration for NonSymmetric Affine Fixed Point Problems and Application to Markov Decision Processes	scientific article; zbMATH DE number 7487114

Statements

instance of

scholarly article

0 references

title

Multiply Accelerated Value Iteration for NonSymmetric Affine Fixed Point Problems and Application to Markov Decision Processes (English)

0 references

0 references

0 references

0 references

0 references

SIAM Journal on Matrix Analysis and Applications

0 references

publication date

10 March 2022

0 references

full work available at URL

https://arxiv.org/abs/2009.10427

0 references

zbMATH Keywords

nonexpansive maps

0 references

dynamic programming

0 references

optimal control

0 references

large scale optimization

0 references

Nesterov acceleration

0 references

value iteration

0 references

Krasnosel'skiĭ-Mann algorithm

0 references

fixed point problems

0 references

describes a project that uses

SuperMann

0 references

Anderson

0 references

MaRDI profile type

MaRDI publication profile

0 references

cites work

Iterative Procedures for Nonlinear Integral Equations

0 references

Q4995610

0 references

Convergence of inertial dynamics and proximal algorithms governed by maximally monotone operators

0 references

Q4894778

0 references

Q3241581

0 references

Approximate policy iteration: a survey and some new methods

0 references

An Analysis of Stochastic Shortest Path Problems

0 references

Q4257216

0 references

Circular law theorem for random Markov matrices

0 references

A General Inertial Proximal Point Algorithm for Mixed Variational Inequality Problem

0 references

Performance of first-order methods for smooth convex minimization: a novel approach

0 references

On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators

0 references

Controlled Markov processes and viscosity solutions

0 references

Strategy Iteration Is Strongly Polynomial for 2-Player Turn-Based Stochastic Games with a Constant Discount Factor

0 references

Q3266141

0 references

A generic online acceleration scheme for optimization algorithms via relaxation and inertia

0 references

Newton-Type Methods for Optimization and Variational Problems

0 references

Q5847510

0 references

Q2703816

0 references

On the convergence rate of the Halpern-iteration

0 references

Mean Value Methods in Iteration

0 references

Q3320132

0 references

Introductory lectures on convex optimization. A basic course.

0 references

Some methods of speeding up the convergence of iteration methods

0 references

Q5305630

0 references

Two classes of multisecant methods for nonlinear acceleration

0 references

Augmented Lagrangians and Applications of the Proximal Point Algorithm in Convex Programming

0 references

Monotone Operators and the Proximal Point Algorithm

0 references

Q5744816

0 references

SuperMann: A Superlinearly Convergent Algorithm for Finding Fixed Points of Nonexpansive Operators

0 references

Anderson Acceleration for Fixed-Point Iterations

0 references

Q3698635

0 references

The Simplex and Policy-Iteration Methods Are Strongly Polynomial for the Markov Decision Problem with a Fixed Discount Rate

0 references

Globally Convergent Type-I Anderson Acceleration for Nonsmooth Fixed-Point Iterations

0 references

Identifiers

zbMATH Open document ID

1486.90203

0 references

DOI

10.1137/20M1367192

0 references

Mathematics Subject Classification ID

0 references

0 references

0 references

0 references

0 references

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:5862806

@@ Property / cites work @@
+Iterative Procedures for Nonlinear Integral Equations
+Normal rank
@@ Property / cites work @@
+Q4995610
@@ Property / cites work: Q4995610 / rank @@
+Normal rank
@@ Property / cites work @@
+Convergence of inertial dynamics and proximal algorithms governed by maximally monotone operators
+Normal rank
@@ Property / cites work @@
+Q4894778
@@ Property / cites work: Q4894778 / rank @@
+Normal rank
@@ Property / cites work @@
+Q3241581
@@ Property / cites work: Q3241581 / rank @@
+Normal rank
@@ Property / cites work @@
+Approximate policy iteration: a survey and some new methods
+Normal rank
@@ Property / cites work @@
+An Analysis of Stochastic Shortest Path Problems
@@ Property / cites work: An Analysis of Stochastic Shortest Path Problems / rank @@
+Normal rank
@@ Property / cites work @@
+Q4257216
@@ Property / cites work: Q4257216 / rank @@
+Normal rank
@@ Property / cites work @@
+Circular law theorem for random Markov matrices
@@ Property / cites work: Circular law theorem for random Markov matrices / rank @@
+Normal rank
@@ Property / cites work @@
+A General Inertial Proximal Point Algorithm for Mixed Variational Inequality Problem
+Normal rank
@@ Property / cites work @@
+Performance of first-order methods for smooth convex minimization: a novel approach
+Normal rank
@@ Property / cites work @@
+On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators
+Normal rank
@@ Property / cites work @@
+Controlled Markov processes and viscosity solutions
+Normal rank
@@ Property / cites work @@
+Strategy Iteration Is Strongly Polynomial for 2-Player Turn-Based Stochastic Games with a Constant Discount Factor
+Normal rank
@@ Property / cites work @@
+Q3266141
@@ Property / cites work: Q3266141 / rank @@
+Normal rank
@@ Property / cites work @@
+A generic online acceleration scheme for optimization algorithms via relaxation and inertia
+Normal rank
@@ Property / cites work @@
+Newton-Type Methods for Optimization and Variational Problems
+Normal rank
@@ Property / cites work @@
+Q5847510
@@ Property / cites work: Q5847510 / rank @@
+Normal rank
@@ Property / cites work @@
+Q2703816
@@ Property / cites work: Q2703816 / rank @@
+Normal rank
@@ Property / cites work @@
+On the convergence rate of the Halpern-iteration
@@ Property / cites work: On the convergence rate of the Halpern-iteration / rank @@
+Normal rank
@@ Property / cites work @@
+Mean Value Methods in Iteration
@@ Property / cites work: Mean Value Methods in Iteration / rank @@
+Normal rank
@@ Property / cites work @@
+Q3320132
@@ Property / cites work: Q3320132 / rank @@
+Normal rank
@@ Property / cites work @@
+Introductory lectures on convex optimization. A basic course.
+Normal rank
@@ Property / cites work @@
+Some methods of speeding up the convergence of iteration methods
+Normal rank
@@ Property / cites work @@
+Q5305630
@@ Property / cites work: Q5305630 / rank @@
+Normal rank
@@ Property / cites work @@
+Two classes of multisecant methods for nonlinear acceleration
+Normal rank
@@ Property / cites work @@
+Augmented Lagrangians and Applications of the Proximal Point Algorithm in Convex Programming
+Normal rank
@@ Property / cites work @@
+Monotone Operators and the Proximal Point Algorithm
+Normal rank
@@ Property / cites work @@
+Q5744816
@@ Property / cites work: Q5744816 / rank @@
+Normal rank
@@ Property / cites work @@
+SuperMann: A Superlinearly Convergent Algorithm for Finding Fixed Points of Nonexpansive Operators
+Normal rank
@@ Property / cites work @@
+Anderson Acceleration for Fixed-Point Iterations
@@ Property / cites work: Anderson Acceleration for Fixed-Point Iterations / rank @@
+Normal rank
@@ Property / cites work @@
+Q3698635
@@ Property / cites work: Q3698635 / rank @@
+Normal rank
@@ Property / cites work @@
+The Simplex and Policy-Iteration Methods Are Strongly Polynomial for the Markov Decision Problem with a Fixed Discount Rate
+Normal rank
@@ Property / cites work @@
+Globally Convergent Type-I Anderson Acceleration for Nonsmooth Fixed-Point Iterations
+Normal rank
@@ Property / OpenAlex ID @@
+W3088211401
@@ Property / OpenAlex ID: W3088211401 / rank @@
+Normal rank