The LP approach in average reward MDPs with multiple cost constraints: The countable state case

DOI10.1080/02522667.1997.10699311zbMath0886.90174OpenAlexW2018101745MaRDI QIDQ4354089

Youqiang Huang, Masami Kurano

Publication date: 10 September 1997

Published in: Journal of Information and Optimization Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/02522667.1997.10699311

zbMATH Keywords

duality gapconstrained optimal stationary policycountable state average reward Markov decision processesmultiple cost constraints

Mathematics Subject Classification ID

Linear programming (90C05) Markov and semi-Markov decision processes (90C40)

Related Items

On Linear Programming for Constrained and Unconstrained Average-Cost Markov Decision Processes with Countable Action Spaces and Strictly Unbounded Costs ⋮ MF-OMO: An Optimization Formulation of Mean-Field Games ⋮ The Lagrange and the vanishing discount techniques to controlled diffusions with cost constraints

Cites Work

• Unnamed Item
• Unnamed Item
• Optimal policies for controlled Markov chains with a constraint
• Average cost Markov decision processes: Optimality conditions
• Finite state Markovian decision processes
• Multichain Markov Decision Processes with a Sample Path Constraint: A Decomposition Approach
• Randomized and Past-Dependent Policies for Markov Decision Processes with Multiple Constraints
• Ergodic Control of Markov Chains with Constraints—the General Case
• Denumerable Constrained Markov Decision Processes and Finite Approximations
• Survey of linear programming for standard and nonstandard Markovian control problems. Part I: Theory
• Linear programming formulation of MDPs in countable state space: The multichain case
• Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
• Markov Decision Processes with Sample Path Constraints: The Communicating Case