The Existence of a Minimum Pair of State and Policy for Markov Decision Processes under the Hypothesis of Doeblin

DOI10.1137/0327016MaRDI QIDQ3833894zbMATH OpenOpenAlexFDO

Authors Masami Kurano

Publication date 1989

Published in SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/0327016

zbMATH Keywords

Doeblin conditionaverage-cost Markov decision processesstationary, uniformly optimal policy

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Recommendations

• Average cost Markov decision processes under the hypothesis of Doeblin
• Average Cost Optimal Stationary Policies in Infinite State Markov Decision Processes with Unbounded Costs
• Functional characterization for average cost Markov decision processes with Doeblin's conditions
• scientific article; zbMATH DE number 3854831
• Average cost Markov decision processes with weakly continuous transition probabilities

Cited in

(21)

• Existence of optimal stationary policies in discounted Markov decision processes: Approaches by occupation measures
• Asymptotic behavior of continuous stochastic games
• Constrained markov decision processes with compact state and action spaces: the average case
• Optimal service control against worst case admission policies: A multichained stochastic game
• Linear programming formulation of MDPs in countable state space: The multichain case
• On Borkar and Young relaxed control topologies and continuous dependence of invariant measures on control policy
• On the Minimum Pair Approach for Average Cost Markov Decision Processes with Countable Discrete Action Spaces and Strictly Unbounded Costs
• scientific article; zbMATH DE number 513084 (Why is no real title available?)
• Average Reward Markov Decision Processes with Multiple Cost Constraints
• Average cost Markov decision processes under the hypothesis of Doeblin
• Average cost Markov decision processes: Optimality conditions
• Functional characterization for average cost Markov decision processes with Doeblin's conditions
• On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes
• Average cost optimal policies for Markov control processes with Borel state space and unbounded costs
• Convex analytic method revisited: further optimality results and performance of deterministic policies in average cost stochastic control
• On structural properties of optimal average cost functions in Markov decision processes with Borel spaces and universally measurable policies
• On the comparison of the stability and control problem of differential systems
• Recurrence conditions for Markov decision processes with Borel state space: A survey
• On linear programming for constrained and unconstrained average-cost Markov decision processes with countable action spaces and strictly unbounded costs
• Optimal control problem for the Lyapunov exponents of random matrix products
• Remarks on the existence of solutions to the average cost optimality equation in Markov decision processes

This page was built for publication: The Existence of a Minimum Pair of State and Policy for Markov Decision Processes under the Hypothesis of Doeblin

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3833894)