Multichain Markov Decision Processes with a Sample Path Constraint: A Decomposition Approach

DOI10.1287/moor.16.1.195zbMath0734.90111OpenAlexW2044387322MaRDI QIDQ3363092

Keith W. Ross, Ravi Varadarajan

Publication date: 1991

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1287/moor.16.1.195

zbMATH Keywords

decompositionlong-run average costfinite action spacefinite state spaceexpected average rewardsample path constraintmultichain Markov decision processes

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (20)

Two-person zero-sum stochastic games ⋮ On some algorithms for limiting average Markov decision processes ⋮ Acceptable strategy profiles in stochastic games ⋮ Constrained Semi-Markov decision processes with average rewards ⋮ Exact decomposition approaches for Markov decision processes: a survey ⋮ The Linear Program approach in multi-chain Markov Decision Processes revisited ⋮ On Bellman's principle with inequality constraints ⋮ A decomposition algorithm for limiting average Markov decision problems. ⋮ STRONG AVERAGE OPTIMALITY FOR CONTROLLED NONHOMOGENEOUS MARKOV CHAINS^* ⋮ The LP approach in average reward MDPs with multiple cost constraints: The countable state case ⋮ Stationary anonymous sequential games with undiscounted rewards ⋮ A note on two-person zero-sum communicating stochastic games ⋮ Constrained Markov decision processes in Borel spaces: from discounted to average optimality ⋮ Stochastic games on a product state space: the periodic case ⋮ Markov control processes with pathwise constraints ⋮ Average Reward Markov Decision Processes with Multiple Cost Constraints ⋮ Communicating zero-sum product stochastic games ⋮ Resource-constrained management of heterogeneous assets with stochastic deterioration ⋮ On constrained Markov decision processes ⋮ Variance-minimization of Markov control processes with pathwise constraints

This page was built for publication: Multichain Markov Decision Processes with a Sample Path Constraint: A Decomposition Approach