On structural properties of optimal average cost functions in Markov decision processes with Borel spaces and universally measurable policies

DOI10.1016/J.JMAA.2021.125954zbMath1483.90175OpenAlexW4200430873MaRDI QIDQ2069795

Huizhen Yu

Publication date: 21 January 2022

Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jmaa.2021.125954

zbMATH Keywords

Markov decision processesreachabilityaverage costrecurrent Markov chainssubmartingalesuniversally measurable policies

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Average control of Markov decision processes with Feller transition probabilities and general action spaces
• On the optimality equation for average cost Markov control processes with Feller transition probabilities
• A convex analytic approach to Markov decision processes
• An expected average reward criterion
• Stochastic optimal control. The discrete time case
• A counterexample on the optimality equation in Markov decision chains with the average cost criterion
• The optimal reward operator in dynamic programming
• The average cost optimality equation: a fixed point approach
• Solutions of the average cost optimality equation for Markov decision processes with weakly continuous kernel: the fixed-point approach revisited
• Recurrence conditions for Markov decision processes with Borel state space: A survey
• Average Cost Markov Decision Processes with Weakly Continuous Transition Probabilities
• General Irreducible Markov Chains and Non-Negative Operators
• Semi-Markov control processes with non-compact action spaces and discontinuous costs
• Markov Chains and Stochastic Stability
• Markov Decision Processes with a Borel Measurable Cost Function—The Average Case
• The Existence of a Minimum Pair of State and Policy for Markov Decision Processes under the Hypothesis of Doeblin
• An $\varepsilon $-Optimal Control of a Finite Markov Chain with an Average Reward Criterion
• Subadditive mean ergodic theorems
• Technical Note—Improved Conditions for Convergence in Undiscounted Markov Renewal Programming
• Alternative Theoretical Frameworks for Finite Horizon Discrete-Time Stochastic Optimal Control
• Universally Measurable Policies in Dynamic Programming
• Linear programming formulation of MDPs in countable state space: The multichain case
• Infinite-horizon Markov control processes with undiscounted cost criteria: from average to overtaking optimality
• The policy iteration algorithm for average reward Markov decision processes with general state space
• Optimal decision procedures for finite Markov chains. Part II: Communicating systems
• Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
• Average Optimality in Dynamic Programming with General State Space
• Real Analysis and Probability
• Fatou's Lemma in Its Classical Form and Lebesgue's Convergence Theorems for Varying Measures with Applications to Markov Decision Processes
• Average Cost Optimality Inequality for Markov Decision Processes with Borel Spaces and Universally Measurable Policies
• On the Minimum Pair Approach for Average Cost Markov Decision Processes with Countable Discrete Action Spaces and Strictly Unbounded Costs
• LP Formulations of Discrete Time Long-Run Average Optimal Control Problems: The NonErgodic Case
• Negative Dynamic Programming
• An Example in Denumerable Decision Processes
• A Borel Set Not Containing a Graph
• Remarks on analytic sets

This page was built for publication: On structural properties of optimal average cost functions in Markov decision processes with Borel spaces and universally measurable policies