Linear programming formulation of MDPs in countable state space: The multichain case

DOI10.1007/BF01414031zbMath0828.90134MaRDI QIDQ4304583

Arie Hordjik, Jean-Bernard Lasserre

Publication date: 12 September 1994

Published in: ZOR - Methods and Models of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf01414031

zbMATH Keywords

average cost criterion; countable state space

Mathematics Subject Classification ID

90C05: Linear programming

90C40: Markov and semi-Markov decision processes

Related Items

The LP approach in average reward MDPs with multiple cost constraints: The countable state case, Constrained markov decision processes with compact state and action spaces: the average case, On Linear Programming for Constrained and Unconstrained Average-Cost Markov Decision Processes with Countable Action Spaces and Strictly Unbounded Costs, Circumventing the Slater conundrum in countably infinite linear programs, LP based upper and lower bounds for Cesàro and Abel limits of the optimal values in problems of control of stochastic discrete time systems, On structural properties of optimal average cost functions in Markov decision processes with Borel spaces and universally measurable policies

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A convex analytic approach to Markov decision processes
• Duality theorem in Markovian decision problems
• Finite state Markovian decision processes
• Linear Programming and Sequential Decisions
• Markov Decision Problems and State-Action Frequencies
• The Existence of a Minimum Pair of State and Policy for Markov Decision Processes under the Hypothesis of Doeblin
• Linear Programming and Markov Decision Chains
• Solving stochastic dynamic programming problems by linear programming — An annotated bibliography
• On Linear Programming in a Markov Decision Problem
• Multichain Markov Renewal Programs