On the Minimum Pair Approach for Average Cost Markov Decision Processes with Countable Discrete Action Spaces and Strictly Unbounded Costs

DOI10.1137/19M1247395zbMath1432.90160arXiv1902.10685MaRDI QIDQ5220188

Huizhen Yu

Publication date: 11 March 2020

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

Full work available at URL: https://arxiv.org/abs/1902.10685

zbMATH Keywords

Markov decision processesBorel state spacecountable actionsmajorization conditionminimum pairstrong and pathwise average cost optimality

Mathematics Subject Classification ID

Dynamic programming (90C39) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)

Related Items (5)

On Linear Programming for Constrained and Unconstrained Average-Cost Markov Decision Processes with Countable Action Spaces and Strictly Unbounded Costs ⋮ A survey of average cost problems in deterministic discrete-time control systems ⋮ Average Cost Optimality Inequality for Markov Decision Processes with Borel Spaces and Universally Measurable Policies ⋮ 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

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stochastic optimal control. The discrete time case
• Average optimality in dynamic programming on Borel spaces -- unbounded costs and controls
• Weak conditions for average optimality in Markov control processes
• Average Cost Markov Decision Processes with Weakly Continuous Transition Probabilities
• General Irreducible Markov Chains and Non-Negative Operators
• A Mixed Value and Policy Iteration Method for Stochastic Control with Universally Measurable Policies
• Markov Chains and Stochastic Stability
• On Minimum Cost Per Unit Time Control of Markov Chains
• Average Cost Optimal Stationary Policies in Infinite State Markov Decision Processes with Unbounded Costs
• The Existence of a Minimum Pair of State and Policy for Markov Decision Processes under the Hypothesis of Doeblin
• Universally Measurable Policies in Dynamic Programming
• The policy iteration algorithm for average reward Markov decision processes with general state space
• Sample-path average optimality for Markov control processes
• Sample path average optimality of Markov control processes with strictly unbounded cost
• Average Optimality in Dynamic Programming with General State Space
• Real Analysis and Probability
• On Linear Programming in a Markov Decision Problem

This page was built for publication: On the Minimum Pair Approach for Average Cost Markov Decision Processes with Countable Discrete Action Spaces and Strictly Unbounded Costs