Markov decision processes (Q5904001): Difference between revisions

The paper is an introduction to Markov decision processes mainly addressed to possible applicants. Therefore it presents a finite model only, but a broad variety of objectives, algorithms (e.g. aggregation), and extensions (e.g. semi-Markov, partially observed, adaptive multiobjective, and constrained models). Some remarks on possible future research are added.

0 references

Mathematics Subject Classification ID

90C40

0 references

0 references

0 references

discrete event dynamic systems

0 references

introduction

0 references

semi-Markov

0 references

partially observed

0 references

adaptive

0 references

multiobjective

0 references

constrained models

0 references

MaRDI profile type

MaRDI publication profile

0 references

full work available at URL

https://doi.org/10.1016/0377-2217(89)90348-2

0 references

0 references

0 references

0 references

Stochastic optimal control. The discrete time case

0 references

Q4209222

0 references

Discounted Dynamic Programming

0 references

Contraction Mappings in the Theory Underlying Dynamic Programming

0 references

Q5561586

0 references

Finite state Markovian decision processes

0 references

On the Optimality of Myopic Policies in Sequential Decision Problems

0 references

Vector-Valued Dynamic Programming

0 references

Q3313617

0 references

Performance evaluation and perturbation analysis of discrete event dynamic systems

0 references

Q3266141

0 references

Q5635252

0 references

Q4739658

0 references

Sequential Decision Problems with Expected Utility Criteria. III: Upper and Lower Transience

0 references

Convergence of Dynamic Programming Models

0 references

A modified dynamic programming method for Markovian decision problems

0 references

Letter to the Editor—A Test for Suboptimal Actions in Markovian Decision Problems

0 references

Q5549539

0 references

An Iterative Aggregation Procedure for Markov Decision Processes

0 references

State of the Art—A Survey of Partially Observable Markov Decision Processes: Theory, Models, and Algorithms

0 references

On Finding the Maximal Gain for Markov Decision Processes

0 references

Suboptimal policy determination for large-scale Markov decision processes. II: Implementation and numerical evaluation

0 references

Some Bounds for Discounted Sequential Decision Processes

0 references

Bounds and Transformations for Discounted Finite Markov Decision Chains

0 references

Modified Policy Iteration Algorithms for Discounted Markov Decision Problems

0 references

Action Elimination Procedures for Modified Policy Iteration Algorithms

0 references

Q5615108

0 references

Q3683893

0 references

Q5602035

0 references

The Asymptotic Behavior of Undiscounted Value Iteration in Markov Decision Problems

0 references

Iterative Aggregation-Disaggregation Procedures for Discounted Semi-Markov Reward Processes

0 references

Sufficient statistics in the optimum control of stochastic systems

0 references

Minimizing a Submodular Function on a Lattice

0 references

Q3912356

0 references

Q4170121

0 references

Q3890445

0 references

Suboptimal Design for Large Scale, Multimodule Systems

0 references

Suboptimal policy determination for large-scale Markov decision processes. I: Description and bounds

0 references

Reward Revision for Discounted Markov Decision Problems

0 references

Parameter Imprecision in Finite State, Finite Action Dynamic Programs

0 references

Reward revision and the average reward Markov decision process

0 references

Markov Decision Processes with Imprecise Transition Probabilities

0 references

Dynamic programming, Markov chains, and the method of successive approximations

0 references

Q3034625

0 references

Q3867541

0 references

Q3856450

0 references

Optimality and efficiency. I

0 references

Multi-objective infinite-horizon discounted Markov decision processes

0 references

A Survey of Applications of Markov Decision Processes

0 references

Infinite horizon Markov decision processes with unknown or variable discount factors

0 references

Mean, variance and probabilistic criteria in finite Markov decision processes: A review

0 references

Approximations of Dynamic Programs, I

0 references

Approximations of Dynamic Programs, II

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:5904001

@@ Property / cites work @@
+Q3241581
@@ Property / cites work: Q3241581 / rank @@
+Normal rank
@@ Property / cites work @@
+Q3286740
@@ Property / cites work: Q3286740 / rank @@
+Normal rank
@@ Property / cites work @@
+Stochastic optimal control. The discrete time case
+Normal rank
@@ Property / cites work @@
+Q4209222
@@ Property / cites work: Q4209222 / rank @@
+Normal rank
@@ Property / cites work @@
+Discounted Dynamic Programming
@@ Property / cites work: Discounted Dynamic Programming / rank @@
+Normal rank
@@ Property / cites work @@
+Contraction Mappings in the Theory Underlying Dynamic Programming
+Normal rank
@@ Property / cites work @@
+Q5561586
@@ Property / cites work: Q5561586 / rank @@
+Normal rank
@@ Property / cites work @@
+Finite state Markovian decision processes
@@ Property / cites work: Finite state Markovian decision processes / rank @@
+Normal rank
@@ Property / cites work @@
+On the Optimality of Myopic Policies in Sequential Decision Problems
+Normal rank
@@ Property / cites work @@
+Vector-Valued Dynamic Programming
@@ Property / cites work: Vector-Valued Dynamic Programming / rank @@
+Normal rank
@@ Property / cites work @@
+Q3313617
@@ Property / cites work: Q3313617 / rank @@
+Normal rank
@@ Property / cites work @@
+Performance evaluation and perturbation analysis of discrete event dynamic systems
+Normal rank
@@ Property / cites work @@
+Q3266141
@@ Property / cites work: Q3266141 / rank @@
+Normal rank
@@ Property / cites work @@
+Q5635252
@@ Property / cites work: Q5635252 / rank @@
+Normal rank
@@ Property / cites work @@
+Q4739658
@@ Property / cites work: Q4739658 / rank @@
+Normal rank
@@ Property / cites work @@
+Sequential Decision Problems with Expected Utility Criteria. III: Upper and Lower Transience
+Normal rank
@@ Property / cites work @@
+Convergence of Dynamic Programming Models
@@ Property / cites work: Convergence of Dynamic Programming Models / rank @@
+Normal rank
@@ Property / cites work @@
+A modified dynamic programming method for Markovian decision problems
+Normal rank
@@ Property / cites work @@
+Letter to the Editor—A Test for Suboptimal Actions in Markovian Decision Problems
+Normal rank
@@ Property / cites work @@
+Q5549539
@@ Property / cites work: Q5549539 / rank @@
+Normal rank
@@ Property / cites work @@
+An Iterative Aggregation Procedure for Markov Decision Processes
+Normal rank
@@ Property / cites work @@
+State of the Art—A Survey of Partially Observable Markov Decision Processes: Theory, Models, and Algorithms
+Normal rank
@@ Property / cites work @@
+On Finding the Maximal Gain for Markov Decision Processes
+Normal rank
@@ Property / cites work @@
+Suboptimal policy determination for large-scale Markov decision processes. II: Implementation and numerical evaluation
+Normal rank
@@ Property / cites work @@
+Some Bounds for Discounted Sequential Decision Processes
+Normal rank
@@ Property / cites work @@
+Bounds and Transformations for Discounted Finite Markov Decision Chains
+Normal rank
@@ Property / cites work @@
+Modified Policy Iteration Algorithms for Discounted Markov Decision Problems
+Normal rank
@@ Property / cites work @@
+Action Elimination Procedures for Modified Policy Iteration Algorithms
+Normal rank
@@ Property / cites work @@
+Q5615108
@@ Property / cites work: Q5615108 / rank @@
+Normal rank
@@ Property / cites work @@
+Q3683893
@@ Property / cites work: Q3683893 / rank @@
+Normal rank
@@ Property / cites work @@
+Q5602035
@@ Property / cites work: Q5602035 / rank @@
+Normal rank
@@ Property / cites work @@
+The Asymptotic Behavior of Undiscounted Value Iteration in Markov Decision Problems
+Normal rank
@@ Property / cites work @@
+Iterative Aggregation-Disaggregation Procedures for Discounted Semi-Markov Reward Processes
+Normal rank
@@ Property / cites work @@
+Sufficient statistics in the optimum control of stochastic systems
+Normal rank
@@ Property / cites work @@
+Minimizing a Submodular Function on a Lattice
@@ Property / cites work: Minimizing a Submodular Function on a Lattice / rank @@
+Normal rank
@@ Property / cites work @@
+Q3912356
@@ Property / cites work: Q3912356 / rank @@
+Normal rank
@@ Property / cites work @@
+Q4170121
@@ Property / cites work: Q4170121 / rank @@
+Normal rank
@@ Property / cites work @@
+Q3890445
@@ Property / cites work: Q3890445 / rank @@
+Normal rank
@@ Property / cites work @@
+Suboptimal Design for Large Scale, Multimodule Systems
+Normal rank
@@ Property / cites work @@
+Suboptimal policy determination for large-scale Markov decision processes. I: Description and bounds
+Normal rank
@@ Property / cites work @@
+Reward Revision for Discounted Markov Decision Problems
+Normal rank
@@ Property / cites work @@
+Parameter Imprecision in Finite State, Finite Action Dynamic Programs
+Normal rank
@@ Property / cites work @@
+Reward revision and the average reward Markov decision process
+Normal rank
@@ Property / cites work @@
+Markov Decision Processes with Imprecise Transition Probabilities
+Normal rank
@@ Property / cites work @@
+Dynamic programming, Markov chains, and the method of successive approximations
+Normal rank
@@ Property / cites work @@
+Q3034625
@@ Property / cites work: Q3034625 / rank @@
+Normal rank
@@ Property / cites work @@
+Q3867541
@@ Property / cites work: Q3867541 / rank @@
+Normal rank
@@ Property / cites work @@
+Q3856450
@@ Property / cites work: Q3856450 / rank @@
+Normal rank
@@ Property / cites work @@
+Optimality and efficiency. I
@@ Property / cites work: Optimality and efficiency. I / rank @@
+Normal rank
@@ Property / cites work @@
+Multi-objective infinite-horizon discounted Markov decision processes
+Normal rank
@@ Property / cites work @@
+A Survey of Applications of Markov Decision Processes
+Normal rank
@@ Property / cites work @@
+Infinite horizon Markov decision processes with unknown or variable discount factors
+Normal rank
@@ Property / cites work @@
+Mean, variance and probabilistic criteria in finite Markov decision processes: A review
+Normal rank
@@ Property / cites work @@
+Approximations of Dynamic Programs, I
@@ Property / cites work: Approximations of Dynamic Programs, I / rank @@
+Normal rank
@@ Property / cites work @@
+Approximations of Dynamic Programs, II
@@ Property / cites work: Approximations of Dynamic Programs, II / rank @@
+Normal rank