Approximation of average cost optimal policies for general Markov decision processes with unbounded costs
From MaRDI portal
Publication:1362682
DOI10.1007/BF01193864zbMath0882.90127OpenAlexW2037038863MaRDI QIDQ1362682
Raúl Montes-De-oca, Adolfo Minjárez-sosa, Evgueni I. Gordienko
Publication date: 5 August 1997
Published in: Mathematical Methods of Operations Research (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/bf01193864
Markov decision processesvalue iterationgeometrical convergenceaverage cost criterionBorel state spaceapproximation of optimal policyLyapunov-like ergodicity conditions
Related Items (1)
Cites Work
- Unnamed Item
- Unnamed Item
- An estimate of the stability of optimal control of certain stochastic and deterministic systems
- A note on the vanishing interest rate approach in average Markov decision chains with continuous and bounded costs
- Markov chains and stochastic stability
- Value iteration in countable state average cost Markov decision processes with unbounded costs
- Stochastic optimal control. The discrete time case
- Equivalence of Lyapunov stability criteria in a class of Markov decision processes
- Measurable selection theorems for optimization problems
- Adaptive Markov control processes
- Value iteration in average cost Markov control processes on Borel spaces
- Dynamic programming, Markov chains, and the method of successive approximations
- Value iteration in a class of average controlled Markov chains with unbounded costs: necessary and sufficient conditions for pointwise convergence
- General Irreducible Markov Chains and Non-Negative Operators
- Adaptive Strategies for Certain Classes of Controlled Markov Processes
- Inequalities in Theorems of Ergodicity and Stability for Markov Chains with Common Phase Space. II
- Perturbation theory for unbounded Markov reward processes with applications to queueing
- Perturbation theory for Markov reward processes with applications to queueing systems
- Perturbation and stability theory for Markov control problems
- The asymptotic behaviour of the minimal total expected cost for the denumerable state Markov decision model
- Sensitive Optimality Criteria in Countable State Dynamic Programming
- Infinite-horizon Markov control processes with undiscounted cost criteria: from average to overtaking optimality
- Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
- Average cost Markov control processes with weighted norms: existence of canonical policies
- Average cost Markov control processes with weighted norms: value iteration
This page was built for publication: Approximation of average cost optimal policies for general Markov decision processes with unbounded costs
