Approximation of average cost optimal policies for general Markov decision processes with unbounded costs
DOI10.1007/BF01193864zbMATH Open0882.90127OpenAlexW2037038863MaRDI QIDQ1362682FDOQ1362682
Authors: Evgueni Gordienko, Raúl Montes-de-Oca, Adolfo Minjárez-sosa 
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
Recommendations
- Average Cost Optimal Stationary Policies in Infinite State Markov Decision Processes with Unbounded Costs
- On strong average optimality of Markov decision processes with unbounded costs
- Average cost Markov decision processes with weakly continuous transition probabilities
- Average cost optimal policies for Markov control processes with Borel state space and unbounded costs
value iterationMarkov decision processesgeometrical convergenceaverage cost criterionBorel state spaceapproximation of optimal policyLyapunov-like ergodicity conditions
Cites Work
- Markov chains and stochastic stability
- General Irreducible Markov Chains and Non-Negative Operators
- Dynamic programming, Markov chains, and the method of successive approximations
- Stochastic optimal control. The discrete time case
- Infinite-horizon Markov control processes with undiscounted cost criteria: from average to overtaking optimality
- Adaptive Markov control processes
- Value iteration in average cost Markov control processes on Borel spaces
- Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
- Average cost Markov control processes with weighted norms: existence of canonical policies
- Title not available (Why is that?)
- Perturbation theory for Markov reward processes with applications to queueing systems
- An estimate of the stability of optimal control of certain stochastic and deterministic systems
- Average cost Markov control processes with weighted norms: value iteration
- Perturbation theory for unbounded Markov reward processes with applications to queueing
- Measurable selection theorems for optimization problems
- Title not available (Why is that?)
- Equivalence of Lyapunov stability criteria in a class of Markov decision processes
- A note on the vanishing interest rate approach in average Markov decision chains with continuous and bounded costs
- Perturbation and stability theory for Markov control problems
- The asymptotic behaviour of the minimal total expected cost for the denumerable state Markov decision model
- Value iteration in countable state average cost Markov decision processes with unbounded costs
- Inequalities in Theorems of Ergodicity and Stability for Markov Chains with Common Phase Space. II
- Adaptive Strategies for Certain Classes of Controlled Markov Processes
- Value iteration in a class of average controlled Markov chains with unbounded costs: necessary and sufficient conditions for pointwise convergence
- Sensitive Optimality Criteria in Countable State Dynamic Programming
Cited In (8)
- Average cost Markov control processes: Stability with respect to the Kantorovich metric
- On the Minimum Pair Approach for Average Cost Markov Decision Processes with Countable Discrete Action Spaces and Strictly Unbounded Costs
- Title not available (Why is that?)
- Approximation of average cost Markov decision processes using empirical distributions and concentration inequalities
- Suboptimal policy determination for large-scale Markov decision processes. I: Description and bounds
- Adaptive control for discrete-time Markov processes with unbounded costs: Discounted criterion.
- Unbounded cost Markov decision processes with limsup and liminf average criteria: new conditions
- Exact finite approximations of average-cost countable Markov decision processes
This page was built for publication: Approximation of average cost optimal policies for general Markov decision processes with unbounded costs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1362682)
