A note on the existence of optimal stationary policies for average Markov decision processes with countable states (Q6163982): Difference between revisions

Revision as of 13:15, 1 August 2024

scientific article; zbMATH DE number 7705219

Language	Label	Description	Also known as
English	A note on the existence of optimal stationary policies for average Markov decision processes with countable states	scientific article; zbMATH DE number 7705219

Statements

instance of

scholarly article

0 references

title

A note on the existence of optimal stationary policies for average Markov decision processes with countable states (English)

0 references

published in

Automatica

0 references

publication date

30 June 2023

0 references

full work available at URL

https://arxiv.org/abs/2007.01602

0 references

zbMATH Keywords

Markov decision process

0 references

countable states

0 references

optimal stationary policy

0 references

metric space

0 references

MaRDI profile type

MaRDI publication profile

0 references

cites work

Q4264741

0 references

Q2925454

0 references

Control of Markov Chains with Long-Run Average Cost Criterion: The Dynamic Programming Equations

0 references

Ergodic Control of Markov Chains with Constraints—the General Case

0 references

Q3827813

0 references

Recent results on conditions for the existence of average optimal stationary policies

0 references

Comparing recent assumptions for the existence of average optimal stationary policies

0 references

Constrained discounted Markov decision processes with Borel state spaces

0 references

Average Cost Markov Decision Processes with Weakly Continuous Transition Probabilities

0 references

Optimality Inequalities for Average Cost Markov Decision Processes and the Stochastic Cash Balance Problem

0 references

Handbook of Markov decision processes. Methods and applications

0 references

Continuous-time Markov decision processes. Theory and applications

0 references

Average optimality for continuous-time Markov decision processes in Polish spaces

0 references

Average optimality in dynamic programming on Borel spaces -- unbounded costs and controls

0 references

Q4255598

0 references

On the optimality equation for average cost Markov control processes with Feller transition probabilities

0 references

Constrained Markov Decision Processes with Expected Total Reward Criteria

0 references

Conditions for existence of average and Blackwell optimal stationary policies in denumerable Markov decision processes

0 references

Weighted Markov decision processes with perturbation

0 references

The policy iteration algorithm for average reward Markov decision processes with general state space

0 references

Algorithms for optimization and stabilization of controlled Markov chains.

0 references

Selected Topics on Continuous-Time Controlled Markov Chains and Markov Games

0 references

Q4315289

0 references

A new condition for the existence of optimal stationary policies in average cost Markov decision processes

0 references

Average Cost Optimal Stationary Policies in Infinite State Markov Decision Processes with Unbounded Costs

0 references

Q4223191

0 references

Identifiers

zbMATH Open document ID

0 references

0 references

10.1016/j.automatica.2023.110877

0 references

Mathematics Subject Classification ID

90C40

0 references

zbMATH DE Number

7705219

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:6163982

@@ Property / cites work @@
+Q4264741
@@ Property / cites work: Q4264741 / rank @@
+Normal rank
@@ Property / cites work @@
+Q2925454
@@ Property / cites work: Q2925454 / rank @@
+Normal rank
@@ Property / cites work @@
+Control of Markov Chains with Long-Run Average Cost Criterion: The Dynamic Programming Equations
+Normal rank
@@ Property / cites work @@
+Ergodic Control of Markov Chains with Constraints—the General Case
+Normal rank
@@ Property / cites work @@
+Q3827813
@@ Property / cites work: Q3827813 / rank @@
+Normal rank
@@ Property / cites work @@
+Recent results on conditions for the existence of average optimal stationary policies
+Normal rank
@@ Property / cites work @@
+Comparing recent assumptions for the existence of average optimal stationary policies
+Normal rank
@@ Property / cites work @@
+Constrained discounted Markov decision processes with Borel state spaces
+Normal rank
@@ Property / cites work @@
+Average Cost Markov Decision Processes with Weakly Continuous Transition Probabilities
+Normal rank
@@ Property / cites work @@
+Optimality Inequalities for Average Cost Markov Decision Processes and the Stochastic Cash Balance Problem
+Normal rank
@@ Property / cites work @@
+Handbook of Markov decision processes. Methods and applications
+Normal rank
@@ Property / cites work @@
+Continuous-time Markov decision processes. Theory and applications
+Normal rank
@@ Property / cites work @@
+Average optimality for continuous-time Markov decision processes in Polish spaces
+Normal rank
@@ Property / cites work @@
+Average optimality in dynamic programming on Borel spaces -- unbounded costs and controls
+Normal rank
@@ Property / cites work @@
+Q4255598
@@ Property / cites work: Q4255598 / rank @@
+Normal rank
@@ Property / cites work @@
+On the optimality equation for average cost Markov control processes with Feller transition probabilities
+Normal rank
@@ Property / cites work @@
+Constrained Markov Decision Processes with Expected Total Reward Criteria
+Normal rank
@@ Property / cites work @@
+Conditions for existence of average and Blackwell optimal stationary policies in denumerable Markov decision processes
+Normal rank
@@ Property / cites work @@
+Weighted Markov decision processes with perturbation
+Normal rank
@@ Property / cites work @@
+The policy iteration algorithm for average reward Markov decision processes with general state space
+Normal rank
@@ Property / cites work @@
+Algorithms for optimization and stabilization of controlled Markov chains.
+Normal rank
@@ Property / cites work @@
+Selected Topics on Continuous-Time Controlled Markov Chains and Markov Games
+Normal rank
@@ Property / cites work @@
+Q4315289
@@ Property / cites work: Q4315289 / rank @@
+Normal rank
@@ Property / cites work @@
+A new condition for the existence of optimal stationary policies in average cost Markov decision processes
+Normal rank
@@ Property / cites work @@
+Average Cost Optimal Stationary Policies in Infinite State Markov Decision Processes with Unbounded Costs
+Normal rank
@@ Property / cites work @@
+Q4223191
@@ Property / cites work: Q4223191 / rank @@
+Normal rank