Adaptive policy-iteration and policy-value-iteration for discounted Markov decision processes

DOI10.1007/BF01415991zbMath0748.90076MaRDI QIDQ3984139

No author found.

Publication date: 27 June 1992

Published in: [https://portal.mardi4nfdi.de/entity/Q3031760 ZOR Zeitschrift f�r Operations Research Methods and Models of Operations Research] (Search for Journal in Brave)

zbMATH Keywords

nonstationary value iterationdiscounted Markov decision processpolicy-iterationasymptotically discount optimal policiespolicy-value-iteration

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Related Items (1)

Adaptive discounted control for piecewise deterministic Markov processes

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A unified approach to adaptive control of average reward Markov decision processes
• Nonstationary Markov decision problems with converging parameters
• Adaptive Markov control processes
• Adaptive Policies in Markov Decision Processes with Uncertain Transition Matrices
• Estimation and control in discounted stochastic dynamic programming
• Learning algorithms for Markov decision processes
• A set of successive approximation methods for discounted Markovian decision problems
• Modified Policy Iteration Algorithms for Discounted Markov Decision Problems
• Approximations of Dynamic Programs, I
• Estimation and control in Markov chains

This page was built for publication: Adaptive policy-iteration and policy-value-iteration for discounted Markov decision processes