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

DOI10.1137/0327016zbMath0677.90085OpenAlexW2087896522MaRDI QIDQ3833894

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)

Related Items

Existence of optimal stationary policies in discounted Markov decision processes: Approaches by occupation measures ⋮ Recurrence conditions for Markov decision processes with Borel state space: A survey ⋮ On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes ⋮ Optimal service control against worst case admission policies: A multichained stochastic game ⋮ Asymptotic behavior of continuous stochastic games ⋮ On Linear Programming for Constrained and Unconstrained Average-Cost Markov Decision Processes with Countable Action Spaces and Strictly Unbounded Costs ⋮ Linear programming formulation of MDPs in countable state space: The multichain case ⋮ 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 comparison of the stability and control problem of differential systems ⋮ Unnamed Item ⋮ Average cost optimal policies for Markov control processes with Borel state space and unbounded costs ⋮ On the Minimum Pair Approach for Average Cost Markov Decision Processes with Countable Discrete Action Spaces and Strictly Unbounded Costs ⋮ Remarks on the existence of solutions to the average cost optimality equation in Markov decision processes ⋮ Average Reward Markov Decision Processes with Multiple Cost Constraints ⋮ On structural properties of optimal average cost functions in Markov decision processes with Borel spaces and universally measurable policies ⋮ Convex analytic method revisited: further optimality results and performance of deterministic policies in average cost stochastic control ⋮ Optimal control problem for the Lyapunov exponents of random matrix products ⋮ Constrained markov decision processes with compact state and action spaces: the average case