Computationally efficient algorithms for on-line optimization of Markov decision processes

DOI10.1016/0005-1098(92)90011-4zbMath0751.90083OpenAlexW2068109419MaRDI QIDQ1190506

S. Singh

Publication date: 26 September 1992

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0005-1098(92)90011-4

zbMATH Keywords

estimationlong-run average costdistributed algorithmsasynchronous algorithmson-line optimization of finite state Markov decision processes

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40) Computational methods for problems pertaining to operations research and mathematical programming (90-08)

Related Items (2)

Model-based average reward reinforcement learning ⋮ Adaptive control of Markov chains with local updates

Cites Work

• Unnamed Item
• Unnamed Item
• Adaptive control of Markov chains with local updates
• A comparison of Jacobi and Gauss-Seidel parallel iterations
• Nonstationary Markov decision problems with converging parameters
• Adaptive Markov control processes
• A Survey of Some Results in Stochastic Adaptive Control
• Learning algorithms for Markov decision processes
• Distributed dynamic programming
• Estimation and control in Markov chains
• On Recurrent Denumerable Decision Processes
• On Finding the Maximal Gain for Markov Decision Processes

This page was built for publication: Computationally efficient algorithms for on-line optimization of Markov decision processes