A forecast horizon and a stopping rule for general Markov decision processes

DOI10.1016/0022-247X(88)90069-8zbMath0646.90090OpenAlexW1989567750MaRDI QIDQ1104254

Jean-Bernard Lasserre, Onésimo Hernández-Lerma

Publication date: 1988

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

Full work available at URL: https://doi.org/10.1016/0022-247x(88)90069-8

zbMATH Keywords

Markov decision processesBorel state spacediscounted and average reward criteriaexistence and detection of a forecast horizonunique optimal stationary policy

Mathematics Subject Classification ID

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

Related Items (10)

Optimality equations and inequalities in a class of risk-sensitive average cost Markov decision chains ⋮ Dual Ascent and Primal-Dual Algorithms for Infinite-Horizon Nonstationary Markov Decision Processes ⋮ Turnpikes in Finite Markov Decision Processes and Random Walk ⋮ Approximate receding horizon approach for Markov decision processes: average reward case ⋮ Nonparametric adaptive control of discounted stochastic systems with compact state space ⋮ Average cost Markov decision processes: Optimality conditions ⋮ The discounted method and equivalence of average criteria for risk-sensitive Markov decision processes on Borel spaces ⋮ A characterization of the optimal risk-sensitive average cost in finite controlled Markov chains ⋮ Solutions of the average cost optimality equation for finite Markov decision chains: Risk-sensitive and risk-neutral criteria ⋮ Denumerable state nonhomogeneous Markov decision processes

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Dynamic programming and stochastic control
• An on-line procedure in discounted infinite-horizon stochastic optimal control
• Conditions for the equivalence of optimality criteria in dynamic programming
• Denumerable Undiscounted Semi-Markov Decision Processes with Unbounded Rewards
• Technical Note—Identifying Forecast Horizons in Nonhomogeneous Markov Decision Processes
• Arbitrary State Markovian Decision Processes
• On Two Recent Papers on Ergodicity in Nonhomogeneous Markov Chains

This page was built for publication: A forecast horizon and a stopping rule for general Markov decision processes