Recursive adaptive control of Markov decision processes with the average reward criterion

DOI10.1007/BF01442397zbMath0723.90085OpenAlexW2093026711MaRDI QIDQ2276895

Rolando Cavazos-Cadena, Onésimo Hernández-Lerma

Publication date: 1991

Published in: Applied Mathematics and Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf01442397

zbMATH Keywords

Borel state and action spacesadditive-noise systemsaverage return criterionrecursive adaptive nonstationary value iteration policyunknown noise distribution

Mathematics Subject Classification ID

Stochastic learning and adaptive control (93E35) Markov and semi-Markov decision processes (90C40)

Related Items (2)

Recurrence conditions for Markov decision processes with Borel state space: A survey ⋮ Recursive adaptive control of Markov decision processes with the average reward criterion

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Adaptive control of discounted Markov decision chains
• Nonparametric adaptive control of discounted stochastic systems with compact state space
• Nonstationary Markov decision problems with converging parameters
• Adaptive Markov control processes
• Recursive adaptive control of Markov decision processes with the average reward criterion
• The average-optimal adaptive control of a Markov renewal model in presence of an unknown parameter
• AVERAGE-OPTIMAL ADAPTIVE POLICIES IN SEMI-MARKOV DECISION PROCESSES INCLUDING AN UNKNOWN PARAMETER
• Estimation and control in discounted stochastic dynamic programming
• Optimal Plans for Dynamic Programming Problems
• Estimation and control in Markov chains

This page was built for publication: Recursive adaptive control of Markov decision processes with the average reward criterion