On linear programming for constrained and unconstrained average-cost Markov decision processes with countable action spaces and strictly unbounded costs
From MaRDI portal
Publication:5085149
Abstract: We consider the linear programming approach for constrained and unconstrained Markov decision processes (MDPs) under the long-run average cost criterion, where the class of MDPs in our study have Borel state spaces and discrete countable action spaces. Under a strict unboundedness condition on the one-stage costs and a recently introduced majorization condition on the state transition stochastic kernel, we study infinite-dimensional linear programs for the average-cost MDPs and prove the absence of a duality gap and other optimality results. Our results do not require a lower-semicontinuous MDP model. Thus, they can be applied to countable action space MDPs where the dynamics and one-stage costs are discontinuous in the state variable. Our proofs make use of the continuity property of Borel measurable functions asserted by Lusin's theorem.
Recommendations
- scientific article; zbMATH DE number 1034051
- The LP approach in average reward MDPs with multiple cost constraints: The countable state case
- Linear programming formulation of MDPs in countable state space: The multichain case
- Linear Programming and Average Optimality of Markov Control Processes on Borel Spaces—Unbounded Costs
- Discounted cost Markov decision processes on Borel spaces: The linear programming formulation
Cites work
- scientific article; zbMATH DE number 4029251 (Why is no real title available?)
- scientific article; zbMATH DE number 1325008 (Why is no real title available?)
- scientific article; zbMATH DE number 1348599 (Why is no real title available?)
- scientific article; zbMATH DE number 513084 (Why is no real title available?)
- scientific article; zbMATH DE number 700091 (Why is no real title available?)
- scientific article; zbMATH DE number 1786124 (Why is no real title available?)
- scientific article; zbMATH DE number 3793773 (Why is no real title available?)
- scientific article; zbMATH DE number 3245885 (Why is no real title available?)
- scientific article; zbMATH DE number 3274494 (Why is no real title available?)
- scientific article; zbMATH DE number 3396557 (Why is no real title available?)
- A convex analytic approach to Markov decision processes
- Average cost optimality inequality for Markov decision processes with Borel spaces and universally measurable policies
- Average optimal stationary policies and linear programming in countable space Markov decision processes
- Constrained Average Cost Markov Control Processes in Borel Spaces
- Constrained Discounted Dynamic Programming
- Constrained Markov control processes in Borel spaces: the discounted case
- Constrained markov decision processes with compact state and action spaces: the average case
- Discretization and Weak Convergence in Markov Decision Drift Processes
- Duality theorem in Markovian decision problems
- Ergodic Control of Markov Chains with Constraints—the General Case
- Handbook of Markov decision processes. Methods and applications
- Infinite Linear Programming and Multichain Markov Control Processes in Uncountable Spaces
- LP Formulations of Discrete Time Long-Run Average Optimal Control Problems: The NonErgodic Case
- Linear Programming and Average Optimality of Markov Control Processes on Borel Spaces—Unbounded Costs
- Linear Programming and Markov Decision Chains
- Linear programming formulation of MDPs in countable state space: The multichain case
- Markov Chains and Stochastic Stability
- Markov chains and invariant probabilities
- Multichain Markov Renewal Programs
- Non-Existence of Everywhere Proper Conditional Distributions
- On Linear Programming in a Markov Decision Problem
- On the Minimum Pair Approach for Average Cost Markov Decision Processes with Countable Discrete Action Spaces and Strictly Unbounded Costs
- Real Analysis and Probability
- Sample path average optimality of Markov control processes with strictly unbounded cost
- Sample-path average optimality for Markov control processes
- Stable sequential control rules and Markov chains
- Stochastic optimal control. The discrete time case
- The Existence of a Minimum Pair of State and Policy for Markov Decision Processes under the Hypothesis of Doeblin
- The LP approach in average reward MDPs with multiple cost constraints: The countable state case
Cited in
(3)
This page was built for publication: On linear programming for constrained and unconstrained average-cost Markov decision processes with countable action spaces and strictly unbounded costs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5085149)
