A unified approach to adaptive control of average reward Markov decision processes

DOI10.1007/BF01740510zbMath0631.90084OpenAlexW2319020649MaRDI QIDQ1095048

Gerhard Hübner

Publication date: 1988

Published in: OR Spektrum (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf01740510

zbMATH Keywords

adaptive controlpolicy improvementnonstationary value iterationadaptive average reward Markov decision

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (2)

Adaptive policy-iteration and policy-value-iteration for discounted Markov decision processes ⋮ Estimation and control in multichain processes

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Adaptive control of discounted Markov decision chains
• Nonstationary Markov decision problems with converging parameters
• Contraction mappings underlying undiscounted Markov decision problems
• Adaptive Policies in Markov Decision Processes with Uncertain Transition Matrices
• Learning algorithms for Markov decision processes
• Bounds and good policies in stationary finite–stage Markovian decision problems
• The optimality equation in average cost denumerable state semi-Markov decision problems, recurrency conditions and algorithms
• Estimation and control in Markov chains

This page was built for publication: A unified approach to adaptive control of average reward Markov decision processes